In traditional mobile networks, trust between subscribers and their serving networks relies on a hardware root of trust: the Subscriber Identity Module (SIM). Conversely, trust between service and home networks is established via Trusted Third Parties (TTPs), known as Clearing Houses (CHs). The 6G environment will witness a substantial increase in subscriber numbers, driven by the mass deployment of the Internet of Everything (IoE) and improvements in network performance. Simultaneously, the performance capabilities required of TTPs to manage trustworthy operator-to-operator (O2O) interactions in 6G must align with the demands of the 6G ecosystem. This work focuses on enhancing CH intermediation capabilities to support O2O trustworthy interactions within the 6G context. Given the close connection between performance and trustworthiness, this paper explores these aspects by modeling interactions between communication parties using a Petri Net model. This model is applied to analyze the quantitative relationships among the non-functional requirements of future 6G communication scenarios, considering both traditional and blockchain-based approaches.

The current Unmanned Aerial Vehicle (UAV) systems lack traceable, secure, private, and trustworthy automated assurance that UAV operations comply with regulatory rules and regulations. In this article, we propose a blockchain-based solution to ensure that the operations of UAVs comply with critical regulatory parameters such as geofencing and operational time restrictions. By utilizing smart contracts and blockchain’s inherent features, such as immutability, data integrity, and decentralization, our proposed system facilitates automated UAV compliance verification, ensures accountable UAV operations, and establishes a secure, private, and trustworthy framework for all stakeholders involved in UAV commercial activities. We leverage Hyperledger Fabric (HLF) to configure and implement a permissioned blockchain network capable of handling transactions amongst all stakeholders, including regulators, service providers, and UAV operators. We present our system architecture and detailed sequence diagrams for compliance assurance of UAV operations. We also discuss the configuration details of the Fabric network, the implementation of the algorithms behind the chaincode, and performance results. We conduct functional validation and evaluate the performance of our implementation in terms of both throughput and latency. The assessment shows that the solution processes over 72,000 beacons per second, making it suitable for large-scale deployment. Furthermore, we compare our proposed solution with the existing solutions to show its superiority. We make our chaincode files, which represent the smart contracts defining the set of rules and processes for a blockchain network, publicly available on GitHub.

ABSTRACT Accurately assessing the energy consumption associated with public buildings and the services they provide is essential for supporting sustainable infrastructure planning. This work presents an integrated modelling framework that combines machine learning prediction of building energy use with a graph based representation of user mobility, allowing a comprehensive estimation of total energy demand. The approach includes building operations, service related energy, travel by users and staff and supply chain logistics. Building energy consumption is predicted through supervised models trained on a curated subset of commercial facilities selected for their similarity to public service environments. Mobility is modelled using a synthetic geographical network that encodes population distribution, available transportation modes, behavioural tendencies and relocation dynamics. The framework is applied to a university reorganization scenario, exploring alternative facility configurations and varying degrees of remote activity. Results indicate that user travel is generally the dominant contributor to total energy demand, while the importance of building energy increases as in person attendance decreases. Sensitivity analyses confirm the robustness of the optimal configurations under different behavioural assumptions. We stress that this is not actually an optimization algorithm, but a parameter sweep; in real situations, constraints may be applied, for instance for building availability, costs, opportunity of sharing services or specific goals. The methodology is further demonstrated in a real healthcare application, where the predictive model enables reliable estimation of building energy use in the absence of direct measurements. Overall, the proposed framework illustrates how data driven modelling and intelligent system techniques can support sustainable decision making for complex public service infrastructures.

• GNN for next event prediction using both prefix and full trace inputs. • Time-decay attention enhances focus on temporally relevant events. • Semantic edge embeddings improve modeling of transition dynamics. • Visual interpretability supports trace level model transparency. Predictive Business Process Monitoring (PBPM) aims to forecast future events in ongoing cases based on historical event logs. While Graph Neural Networks (GNNs) are well suited to capture structural dependencies in process data, existing GNN-based PBPM models remain underdeveloped. Most rely either on short prefix subgraphs or global architectures that overlook temporal relevance and transition semantics. We propose a unified, interpretable GNN framework that advances the state of the art along three key axes. First, we compare prefix-based Graph Convolutional Networks(GCNs) and full trace Graph Attention Networks(GATs) to quantify the performance gap between localized and global modeling. Second, we introduce a novel time decay attention mechanism that constructs dynamic, prediction-centered windows, emphasizing temporally relevant history and suppressing noise. Third, we embed transition type semantics into edge features to enable fine grained reasoning over structurally ambiguous traces. Our architecture includes multilevel interpretability modules, offering diverse visualizations of attention behavior. Evaluated on six benchmarks with different decay factors, the proposed models achieve competitive Top- k accuracy and Damerau-Levenshtein scores under a consistent global setup. A separate analysis of the decay coefficient λ confirms its role in adapting attention, with effective values calibrated by temporal structure and sequence depth. By addressing architectural, temporal, and semantic gaps, this work presents a robust, generalizable, and explainable solution for next event prediction in PBPM.

• The proposed SWF tokenization method, dynamically capturing emotional subtleties, noise robustness, and contextual information to robustly preserve speaker identity. • A transformative deep-self-supervised spectrogram transformer back-end, outperforming conventional approaches by effectively addressing their inherent limitations in preserving local features without the need for extensive labeled training data. • Complete elimination of dependency on additional speech enhancement, enabling seamless, efficient, and robust end-to-end learning tailored for real-world deployments. Identifying speakers in noisy and emotional conditions remains a significant challenge due to the distortion of spectral cues. This study proposes the Speech Without Filter (SWF) framework, a novel self-supervised learning paradigm that operates directly on raw spectrograms. Theoretically, this research introduces a progressive tokenization mechanism that acts as a structural inductive bias, mimicking the contracting path of a U-Net to preserve local spectro-temporal continuity. Unlike standard fixed-patch Transformers that often smooth over speaker-specific micro-textures, the SWF architecture integrates denoising and feature extraction into a single stage, challenging the traditional decoupled paradigm of speech enhancement and recognition. Using a sample of 1.58 million pre-training instances, the model was evaluated across English (RAVDESS), Arabic (ESD), and stressful (SUSAS) datasets. Results demonstrate significant improvements, with the SWF model achieving 91.01% accuracy in clean conditions and maintaining 88.5% in high-noise cocktail party environments, outperforming state-of-the-art models like WavLM and HuBERT. These findings suggest that architectural innovation in tokenization is as critical as pre-training scale for robust speech processing.

Uncertainty-aware consistency learning is one of the reliable approaches in semi-supervised medical image segmentation, enforcing robust model predictions under various perturbations. However, existing methods often rely on multiple stochastic predictions or dual-network/decoder discrepancies to estimate uncertainty, which increases computational cost and discards uncertain regions, potentially missing complex structures such as ambiguous lesion boundaries. To address these challenges, we introduce a Dual Uncertainty-Guided Consistency and Regional Contrastive Learning (DUCore) framework. DUCore improves segmentation robustness by integrating two complementary loss functions within consistency learning. The dual uncertainty-guided consistency loss (DuCL) adaptively calibrates the prediction alignment by prioritizing uncertain regions. DuCL uses deterministic single-pass uncertainty estimation, employing entropy-based calibration for aleatoric uncertainty and Proxy Dirichlet calibration for epistemic uncertainty. These uncertainty measures are computed directly from network output, and moderately uncertain regions are weighted instead of being discarded, which preserves valuable learning signals. The Regional Contrastive Loss (ReCL) further refines feature separability using boundary- and gradient-based hard negative mining in the encoded representation space. By explicitly targeting structural ambiguities, ReCL distinguishes lesion and organ edges from visually similar boundary-adjacent regions and mitigates intensity overlaps in gradient-rich transitions. As a result, DUCore is able to delineate fine structures and complex boundaries with higher precision. Extensive experiments on various medical segmentation benchmarks reveal that DUCore outperforms existing consistency methods.

Abstract Accurate delineation of lesions in prostate MRI is crucial for the diagnosis of prostate cancer. Manual segmentation is time-consuming, requires advanced medical expertise, and is subject to inter-operator variability. Automatic lesion segmentation therefore represents a valuable tool to support clinicians by reducing workload, minimizing observer bias, and enabling more consistent image analysis. In this work, we investigated the performance of four deep learning architectures for prostate lesion segmentation: nnU-Net, DenseUNet, SegResUNet, and U-Net. Unlike many existing studies that rely on publicly available data, we constructed a dedicated dataset to better capture real-world variability and challenges. The dataset, comprising T2-weighted (T2W), apparent diffusion coefficient (ADC), and diffusion-weighted imaging (DWI) sequences, was carefully annotated by medical experts to ensure high-quality labels. Training was performed using the full combination of these modalities. Two cohorts were considered based on lesion severity, as defined by PI-RADS (Prostate Imaging–Reporting and Data System) scores: one with only PI-RADS 4–5 lesions (151 patients), and another including PI-RADS 3 cases, totaling 209 patients. Evaluation was conducted both on a patient-by-patient basis and in a consolidated all-patient setting. In the patient-level analysis, nnU-Net achieved the highest Dice similarity coefficient (DSC) of 0.60 when trained on PI-RADS 4–5 lesions, while in the all-patient analysis, DenseUNet attained a DSC of 0.57 on the same dataset. These results are within the range reported in recent prostate lesion segmentation studies, and in some cases are comparable to or exceed those obtained with substantially larger datasets.

Advancements in Computer-Aided Screening (CAS) systems are essential for improving the detection of security threats in X-ray baggage scans. However, current datasets are limited in representing real-world, sophisticated threats and concealment tactics, and existing approaches are constrained by a closed-set paradigm with predefined labels. To address these challenges, we introduce STCray, the first multimodal X-ray baggage security dataset, comprising 46,642 image-caption paired scans across 21 threat categories, generated using an X-ray scanner for airport security. STCray is meticulously developed with our specialized protocol that ensures domain-aware, coherent captions, that lead to the multi-modal instruction following data in X-ray baggage security. This allows us to train a domain-aware visual AI assistant named STING-BEE that supports a range of vision-language tasks, including scene comprehension, referring threat localization, visual grounding, and visual question answering (VQA), establishing novel baselines for multi-modal learning in X-ray baggage security. Further, STING-BEE shows state-of-the-art generalization in cross-domain settings. Code, data, and models are available at https://divs1159.github.io/STING-BEE/.

The ever-increasing interest in and widespread diffusion of Machine Learning (ML)-based applications has driven a substantial amount of research into offensive and defensive ML. ML models can be attacked from different angles: poisoning attacks, the focus of this paper, inject maliciously crafted data points in the training set to modify the model behavior; adversarial attacks maliciously manipulate inference-time data points to fool the ML model and drive the prediction of the ML model according to the attacker’s objective. Ensemble-based techniques are among the most relevant defenses against poisoning attacks and replace the monolithic ML model with an ensemble of ML models trained on different (disjoint) subsets of the training set. They assign data points to the training sets of the models in the ensemble (routing) randomly or using a hash function, assuming that evenly distributing poisoned data points positively influences ML robustness. Our paper departs from this assumption and implements a risk-based ensemble technique where a risk management process is used to perform a smart routing of data points to the training sets. An extensive experimental evaluation demonstrates the effectiveness of the proposed approach in terms of its soundness, robustness, and performance.

In recent years, malware attacks have become more and more sophisticated, reflecting a radical change in malware behavior. Attackers aim to create malware that, at each execution, generates a different number of independent and cooperating threads. Randomization of malware's division of labor among threads poses significant challenges to traditional detection approaches. In this paper, we demonstrate that attacks based on random division of labor among multiple threads can dramatically degrade the detection performance of five benchmark ML models, in some cases dropping their accuracy to 50% with only a few threads. Then, we propose and evaluate a novel detection technique based on polymorphic-aware training and ensemble learning with ad-hoc voting scheme (favoring minority report ). Results of experimentation carried out on real malware system call logs and assigned to threads via a Bayesian splitting accounting for inter-call dependency indicate that our ensemble has high detection capabilities (99.7% best case), and improves the baseline accuracy of a single model in detecting single-thread malware.

Modern applications are increasingly driven by Machine Learning (ML) models whose non-deterministic behavior is affecting the entire application life cycle from design to operation. The pervasive adoption of ML is urgently calling for approaches that guarantee a stable non-functional behavior of ML-based applications over time and across model changes. To this aim, non-functional properties of ML models, such as privacy, confidentiality, fairness, and explainability, must be monitored, verified, and maintained. Existing approaches mostly focus oni)implementing solutions for classifier selection according to the functional behavior of ML models,ii)finding new algorithmic solutions, such as continuous re-training. In this paper, we propose a multi-model approach that aims to guarantee a stable non-functional behavior of ML-based applications. An architectural and methodological approach is provided to compare multiple ML models showing similar non-functional properties and select the model supporting stable non-functional behavior over time according to (dynamic and unpredictable) contextual changes. Our approach goes beyond the state of the art by providing a solution that continuously guarantees a stable non-functional behavior of ML-based applications, is ML algorithm-agnostic, and is driven by non-functional properties assessed on the ML models themselves. It consists of a two-step process working during application operation, wheremodel assessmentverifies non-functional properties of ML models trained and selected at development time, andmodel substitutionguarantees continuous and stable support of non-functional properties. We experimentally evaluate our solution in a real-world scenario focusing on non-functional property fairness.

A warm welcome to the 2024 IEEE World Congress on Services (SERVICES). With Professor Zhi Jin and Professor Michael Sheng serving as the Congress General Chairs, I trust everyone will have a rewarding experience participating in the IEEE Computer Society's flagship annual event in services computing, whether attending on-site or remotely.

A warm welcome to the 2024 IEEE World Congress on Services (SERVICES). With Professor Zhi Jin and Professor Michael Sheng serving as the Congress General Chairs, I trust everyone will have a rewarding experience participating in the IEEE Computer Society's flagship annual event in services computing, whether attending on-site or remotely.

A large literature is available on quantization for communication efficiency in distributed learning. However, these studies often overlook the enhancement of privacy through quantization. This paper aims to fill this research gap by undertaking a systematic literature review on the use of quantization in distributed learning for privacy enhancement. We explore peer-reviewed literature that utilizes quantization for privacy-preserving purposes. Our analysis identifies the limitations and challenges of current approaches. It also highlights the need to integrate quantization techniques for dual objectives (privacy and communication efficiency) in distributed learning frameworks.

The Microgrid allows for more efficient and lower-cost power provisions, and is therefore more flexible than traditional power ecosystems. However, the increasingly integrated nature of these systems into network and internet-connected IT systems also potentially makes them susceptible to cyber-attack. This paper examined different challenges related to the cyber attacks threatening wireless microgrid systems from the experimental view. Wireless communication and transmission methods are widely used for secondary control of energy re-sources. However, there are risks of cyber attacks during the communication process, such as Denial-of-Service (DoS) attacks. This paper reports the investigation of potential cyber attacks on wireless communications of microgrid systems. Furthermore, this paper evaluates the practical impacts of cybersecurity breaches targeting microgrid systems, with special attention to those in Australia. In brief, the main goal of this paper is to enhance the mitigation countermeasures for cyber attacks linked to wireless microgrid systems, thus guaranteeing reliable wireless communications within these systems.

Analyzing packet loss, whether resulting from communication challenges or malicious attacks, is vital for broadcast authentication protocols. It ensures legitimate and continuous authentication across networks. While previous studies have mainly focused on countering Denial of Service (DoS) attacks' impact on packet loss, our research introduces an innovative investigation into packet loss and develops data recovery within variant TESLA protocols. We highlight the efficacy of our proposed hybrid TLI-µTESLA protocol in maintaining continuous and robust connections among network members, while maximizing data recovery in adverse communication conditions. The study examines the unique packet structures associated with each TESLA protocol variant, emphasizing the implications of losing each type on the network performance. We also introduce modifications to variant TESLA protocols to improve data recovery and alleviate the effects of packet loss. Using Java programming language, we conducted simulation analyses that illustrate the adaptability of variant TESLA protocols in recovering lost packet keys and authenticating previously buffered packets, all while maintaining continuous and robust authentication between network members. Our findings also underscore the superiority of the hybrid TLI-µTESLA protocol in terms of packet loss performance and data recovery, alongside its robust cybersecurity features, including confidentiality, integrity, availability, and accessibility. Additionally, we demonstrated the efficiency of our proposed protocol in terms of low computational and communication requirements compared to earlier TESLA protocol variants, as outlined in previous publications.

This article presents a novel framework for integrating low-earth orbit satellites (LEOSs) with terrestrial-wired networks to improve coverage, throughput, and transmission reliability of 6th generation (6G) Internet of things (IoT) networks. The proposed framework utilizes the synergy of non-orthogonal multiple access (NOMA), automatic repeat request (ARQ), and cooperative communications to maximize the data downloaded from a LEOS to multiple terrestrial users. More specifically, we propose a novel offline packets repair and recovery (PRR) technique to reduce the number of dropped packets, where the wired-terrestrial connection is used to enable efficient bidirectional cooperation, to improve the reliability of the received data by reducing the multiuser interference inherent to NOMA. Moreover, by exchanging the acknowledgment messages used with ARQ, efficient Chase combining (CC) is applied to improve the signal to noise ratio (SNR) of the received packets. Extensive Monte Carlo simulation experiments are used to evaluate and quantify the advantages of the proposed system. The results obtained show that the proposed system can repair a significant number of dropped packets, which reduces the packet drop rate and improves the network throughput. In several scenarios, the proposed PRR managed to repair and recover more than 90% of the dropped packets.

The rapid integration of IoT devices into everyday decision-making processes underscores the need for continuous user authentication and data integrity checking during network communication, all while minimizing energy consumption to extend device lifespan. This paper introduces the Bio-Integrated Hybrid TESLA protocol, which is a fully symmetric and energy-efficient authentication protocol designed for resource-constrained IoT devices. Based on the Hybrid TLI-lTESLA protocol, this innovative solution prioritizes high cybersecurity levels and minimal computational requirements for continuous authentication. An innovative advancement involves eliminating the public cryptography process during the synchronization stage of TESLA protocols. Instead, biometric authentication through distorted fingerprint and EEG templates is employed, to establish a non-shared symmetric session key, utilized only once. Furthermore, neither the key nor the original biometric templates are transmitted over the network, ensuring user identity preservation and effectively resolving the key distribution challenge inherent in symmetric cryptography. By offloading intensive tasks to servers and avoiding the storage or transmission of biometric data, the proposed approach conserves IoT device energy and enhances cybersecurity. Simulation analyses and cybersecurity assessments demonstrate successful synchronization, privacy preservation, and low computational demands compared to existing protocols, making the Bio-Integrated Hybrid TESLA protocol a significant advancement in IoT authentication.

Spatial Modulation (SM) has been proposed as a multiple-input-multiple-output (MIMO)-based technique to overcome the inter-channel interference experienced in conventional MIMO systems. It has been further shown that SM enhances energy efficiency and reduces the receiver’s complexity. Nevertheless, under high antenna correlation scenarios, the detection performance of the antenna indices degrades significantly. To address this critical concern, in this paper, we propose three autoencoder-based frameworks for spatial modulation. The first scenario, similar to conventional spatial modulation, trains the encoder for data modulation and the decoder for data demodulation as well as antenna index detection. The performance of this framework deteriorates in high antenna correlation scenarios. Therefore, two novel solutions are presented to embed the antenna index into the transmitted signal in order to reduce the receiver’s reliance on the channel conditions. The first framework adds a phase-shift keying-based antenna signature, while the other trains the encoder to learn an appropriate antenna index embedding. Simulation results show that the two enhanced frameworks result in a significantly enhanced performance, compared to conventional spatial modulation, in terms of block error rate and power efficiency under a high correlation setup (about 18 dB and 24 dB gain, respectively, at a Rician factor of 20 dB).

Autonomous X-ray baggage security screening has shown significant strides recently, proving itself a viable solution to the flaws in manual screening, thanks to advancements in deep learning. However, these data-hungry techniques feed on extensively annotated data involving strenuous labor, impeding their advances in baggage screening. Consequently, we present a context-aware transformer for weakly supervised localization to relieve the annotation burden and provide visual interpretability that aids screeners in threat recognition and researchers in identifying the pitfalls of existing systems. The proposed approach can generalize and localize different types of contraband with only cost-effective binary labels without explicit training on item detection. Context extraction block, integrated into the dual-token framework, generates threat-aware context maps, while the token scoring block focuses on minimizing partial activations. Experimental results surpass state of the art (SOTA) methods in terms of classification and localization accuracies. Furthermore, we analyze failures to determine current vulnerabilities and provide new insights for future research.

The growing adoption of microservice architectures (MSAs) has led to major research and development efforts to address their challenges and improve their performance, reliability, and robustness. Important aspects of MSA that are not sufficiently covered in the open literature include efficient cloud resource allocation and optimal power management. Other aspects of MSA remain widely scattered in the literature, including cost analysis, service level agreements (SLAs), and demand-driven scaling. In this article, we examine recent cloud frameworks for containerized microservices with a focus on efficient resource utilization using auto-scaling. We classify these frameworks on the basis of their resource allocation models and underlying hardware resources. We highlight current MSA trends and identify workload-driven resource sharing within microservice meshes and SLA streamlining as two key areas for future microservice research.

One major advantage of microservice cloud architectures is the agility with which microservices can be replicated to help improve the overall quality of service and meet service-level contracts. Their challenge is to carefully balance the horizontal microservice replicas with the vertical resources of CPU, memory, and IO that are allocated to each microservice. The objective of such balancing act is, of course, to avoid both service bottlenecks and resource wastage. In this paper, we present OSμS, a new open-source microservice prototyping platform that has been developed and instrumented from the ground up with the objective of collecting fine-grained, non-proprietary metrology on microservice mesh performance. We will illustrate the use of OSμS for developing and evaluating machine-learning algorithms for the horizontal and vertical autoscaling of microservice architectures. A hybrid algorithm based on decision-tree learning will be implemented on OSμS and compared with the academic state of the art and existing cloud-provider solutions. The advantages of such algorithm in improving horizontal and vertical resource utilization will be highlighted.

To facilitate the Edge AI paradigm in distributed networks, we propose novel collaborative learning methodologies for a connected network of edge nodes. Our proposed methodologies tackle the challenges in distributed learning where there are constraints on data privacy and a low degree of overlap between the classes observed by the nodes. These approaches entail sharing class distribution information between nodes, computing nodes, and class weights, training local models on each node, then aggregating the models using the determined weights. It favors nodes that have encountered unique or less common classes in their local datasets. Through a series of experiments using an activity recognition dataset, we demonstrate the effectiveness and scalability of our proposed approaches. We show the adaptive nature of the proposed approach by achieving classification accuracy above the baseline, even with little overlap between the observed classes. This study serves as a foundation for future advancements in collaborative learning on edge networks, and encourages the development of scalable solutions.

Recent advances in deep learning have facilitated significant progress in the autonomous detection of concealed security threats from baggage X-ray scans, a plausible solution to overcome the pitfalls of manual screening. However, these data-hungry schemes rely on extensive instance-level annotations that involve strenuous skilled labor. Hence, this paper proposes a context-aware transformer for weakly supervised baggage threat localization, exploiting their inherent capacity to learn long-range semantic relations to capture the object-level context of the illegal items. Unlike the conventional single-class token transformers, the proposed dual-token architecture can generalize well to different threat categories by learning the threat-specific semantics from the token-wise attention to generate context maps. The framework has been evaluated on two public datasets, Compass-XP and SIXray, and surpassed other SOTA approaches.

In this paper, we improve the robustness of Machine Learning (ML) classifiers against training-time attacks by linking the risk of training data being tampered with to the redundancy in the ML model's design needed to prevent it. Our defense mechanism is directly applicable to classifiers' training data, without any knowledge of the specific ML model to be hardened. First, we compute the training data proximity to class separation surfaces, identified via a reference linear model. Each data point is associated with a risk index, which is used to partition the training set by an unsupervised technique. Then, we train a learner for each partition and combine the learners' output in an ensemble. Our method treats the protected ML classifier as a black box and is inherently robust to transfer attacks. Experiments show that, for data poisoning rates between 6 and 25 percent of the training set, our method is more robust compared to benchmarks and to a monolithic version of the model trained on the whole training set. Our results make a convincing case for adopting training set partitioning and ensemble generation as a stage of ML models' development and deployment lifecycle.

In this paper, we propose Value Iteration Network for Reward Shaping (VIN-RS), a potential-based reward shaping mechanism using Convolutional Neural Network (CNN). The proposed VIN-RS embeds a CNN trained on computed labels using the message passing mechanism of the Hidden Markov Model. The CNN processes images or graphs of the environment to predict the shaping values. Recent work on reward shaping still has limitations towards training on a representation of the Markov Decision Process (MDP) and building an estimate of the transition matrix . The advantage of VIN-RS is to construct an effective potential function from an estimated MDP while automatically inferring the environment transition matrix. The proposed VIN-RS estimates the transition matrix through a self-learned convolution filter while extracting environment details from the input frames or sampled graphs. Due to (1) the previous success of using message passing for reward shaping; and (2) the CNN planning behavior, we use these messages to train the CNN of VIN-RS. Experiments are performed on tabular games, Atari 2600 and MuJoCo, for discrete and continuous action space. Our results illustrate promising improvements in the learning speed and maximum cumulative reward compared to the state-of-the-art. The improvement achieved by VIN-RS can only be observed for some of the games due to the underlying nature of some environments. In terms of the studied MuJoCo games, there is on average an increase of 30% in the maximum reward reached during early stages of learning.

Driven by privacy concerns and the promise of Deep Learning, researchers have devoted significant effort to exploring the applicability of Machine Learning (ML). In the domains of communication, network, and service management, ML-based decision-making solutions are eagerly sought to replace traditional model-driven approaches, addressing the growing complexity and heterogeneity of modern systems. In this context, Federated Learning (FL) has gained increasing interest as a decentralized approach that overcomes the limitations of centralized systems for data analysis.

Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision/making processes and even outperforming humans in some tasks. This huge progress in terms of prediction quality does not however find a counterpart in the security of such models and corresponding predictions, where perturbations of fractions of the training set (poisoning) can seriously undermine the model accuracy. Research on poisoning attacks and defenses received increasing attention in the last decade, leading to several promising solutions aiming to increase the robustness of machine learning. Among them, ensemble-based defenses, where different models are trained on portions of the training set and their predictions are then aggregated, provide strong theoretical guarantees at the price of a linear overhead. Surprisingly, ensemble-based defenses, which do not pose any restrictions on the base model, have not been applied to increase the robustness of random forest models. The work in this paper aims to fill in this gap by designing and implementing a novel hash-based ensemble approach that protects random forest against untargeted, random poisoning attacks. An extensive experimental evaluation measures the performance of our approach against a variety of attacks, as well as its sustainability in terms of resource consumption and performance, and compares it with a traditional monolithic model based on random forest. A final discussion presents our main findings and compares our approach with existing poisoning defenses targeting random forests.

Gathering the training malware traces is restive and can be a nuisance depending on the type of malware, such as behavioral polymorphism. Generative Adversarial Networks (GANs) are well suited for these issues because they can generate synthetic data that mimic actual data. This treatise sheds detailed and thorough insights into the GAN model implemented to generate a proper training mechanism for binary classification. This paper tested tabular-based and pictorial-based models in multiple trials to determine the better one for classification. Furthermore, multiple ML-based classification techniques, such as ensemble learning, Support Vector Machines (SVMs), and Linear Regression, were tested and recorded on tabular and pictorial GANs. Tabular-wise, the ∆RMSEdata collected for Random Forest Tree with the Vanilla LeakyReLU-based GAN provided the optimal classification results. Feature interactions and a biological-inspired activation function were considered for optimizing the model. However, they were only additional tests that were not considered part of the leading paper, as testing quantity was insufficient for definitive evidence of optimization.

Malware visualization analysis incorporating with Machine Learning (ML) has been proven to be a promising solution for improving security defenses on different platforms. In this work, we propose an integrated framework for addressing common problems experienced by ML utilizers in developing malware detection systems. Namely, a pictorial presentation system with extensions is designed to preserve the identities of benign/malign samples by encoding each variable into binary digits and mapping them into black and white pixels. A conditional Generative Adversarial Network based model is adopted to produce synthetic images and mitigate issues of imbalance classes. Detection models architected by Convolutional Neural Networks are for validating performances while training on datasets with and without artifactual samples. Result demonstrates accuracy rates of 98.51% and 97.26% for these two training scenarios.

Autonomous detection of threat items from baggage X-ray imagery is one of the most vital and challenging tasks. Manual detection of these items is a cumbersome, slow, and error-ridden process which is also limited by the examination capacity of the security inspector. To overcome these limitations, many researchers have proposed deep learning-driven approaches to recognize suspicious objects from the baggage X-ray scans. However, threat items are rarely seen in the real world compared to innocuous baggage content. Therefore, when trained with imbalanced data, the performance of the conventional threat detection models drastically decreases. This paper addresses these issues with a contour-driven instance segmentation model optimized with a novel combined loss function, dubbed balanced affinity loss function. In addition to mitigating the class imbalance, this function best handles the fine-grained classification aspect inferred by contours and the instance segmentation. We validated the proposed system on three public baggage X-ray datasets, where it outperformed state-of-the-art methods by 7.76%, 25.81%, and 8.78% in terms of intersection-over-union score.

Online process mining refers to a class of techniques for analyzing in real-time event streams generated by the execution of business processes. These techniques are crucial in the reactive monitoring of business processes, timely resource allocation and detection/prevention of dysfunctional behavior. Many interesting advances have been made by the research community in recent years, but there is no consensus on the exact set of properties these techniques have to achieve. This paper tills the gap by identitying a set of evaluation goals for online process mining and examining their fulfillment in the state of the art. We discuss parameters and techniques regulating the balance between conflicting goals and outline research needed for their improvement. Concept drift detection is crucial in this sense but, as demonstrated by our experiments, it is only partially supported by current solutions.

With the emergence of Android malware and be-havioral polymorphism, it has been increasingly popular to use advanced machine learning and deep learning approaches for malware detection. Despite the fact that such classifiers have proven accurate in real-life settings, they remain uninterpretable and difficult for analysts and users to comprehend how they arrive at their classification decisions. Considering that the exfiltration of sensitive information is one of the most significant security threats, we examined both monograms and trigrams of system calls for normal and malicious software and received higher detection accuracy by using the trigram dataset. Based on this, we propose an auxiliary architecture for model explainability of complex data features via enhancement and aggregation of the auxiliary model with the main model based on the degree of disagreement between the two models. In this study, we employ the SHAP (Shapley Additive Explanations) framework to interpret the random forest models in order to identify the features most influential in predicting the model's predictions, along with quantifying their contributions to individual predictions. The obtained results confirm that the models are not biased and the features that influence the classification prediction are intuitive in terms of the exfiltration problem in question. In addition, our proposed methodology increases transparency and interpretability of our exfiltration detection model running in production, increasing the users' trust in the model's predictions.

The increasing number of Internet of Things (IoT) devices and low-cost sensors have facilitated developments in large-scale monitoring applications. However, the accuracy of low-cost sensors remains questionable. Monitoring applications, such as environmental monitoring, try to detect “interesting” data points or patterns, known as anomalies, that do not conform to the norm. These include erroneous data caused by hardware failures or malicious attacks, and nonerroneous data due to unexpected phenomenon, caused by events, such as unexpected high traffic volume. Traditionally, IoT devices collect raw data and periodically upload them to the cloud for processing, which includes anomaly detection. However, the increasing processing capabilities of IoT devices have made the on-device anomaly detection possible in an online and real-time manner. In this article, multivariate long short-term memory (LSTM) autoencoder is proposed for anomaly and event detection in IoT devices. In addition, the proposed approach integrates smart inference, based on a game-theoretical approach, which dynamically changes the period of detection based on the stability of the data, aiming to optimize power consumption and elongate the lifetime of the device. The proposed anomaly and event detection model was simulated and implemented on an STM32H743 Nucleo board, and results show the robustness of the model regardless of the number of anomalies and events present.

It is widely recognised that the process of public health policy making (i.e., the analysis, action plan design, execution, monitoring and evaluation of public health policies) should be evidenced based, and supported by data analytics and decision-making tools tailored to it. This is because the management of health conditions and their consequences at a public health policy making level can benefit from such type of analysis of heterogeneous data, including health care devices usage, physiological, cognitive, clinical and medication, personal, behavioural, lifestyle data, occupational and environmental data. In this paper we present a novel approach to public health policy making in a form of an ontology, and an integrated platform for realising this approach. Our solution is model-driven and makes use of big data analytics technology. More specifically, it is based on public health policy decision making (PHPDM) models that steer the public health policy decision making process by defining the data that need to be collected, the ways in which they should be analysed in order to produce the evidence useful for public health policymaking, how this evidence may support or contradict various policy interventions (actions), and the stakeholders involved in the decision-making process. The resulted web-based platform has been implemented using Hadoop, Spark and HBASE, developed in the context of a research programme on public health policy making for the management of hearing loss called EVOTION, funded by the Horizon 2020.

Information-Centric Networking is an emerging alternative to host-centric networking designed for large-scale content distribution and stricter privacy requirements. Recent research on Information-Centric Networking focused on the protection of the network from attacks targeting the content delivery protocols, while assuming genuine content can always be retrieved from trustworthy nodes. In this paper, we depart from the assumption of the trustworthiness of network nodes and propose a novel certification methodology for information-centric networks that supports continuous security verification of non-functional properties. Our methodology provides a complete and detailed view of the network security status, increasing the trustworthiness of the network and its services. The proposed approach builds on an enhanced certification model capturing the evolution of the system over time. It also defines certification services that fully integrate with existing networks to collect evidence on the target of certification and carry out the certification process. It finally proposes two certification processes, centralized and decentralized, balancing the impact on the network and the system performance. Efficiency, performance, and soundness of our approach are experimentally evaluated in a simulated Named Data Networking (NDN) network targeting property availability.

The rise of the Internet has enabled new types of relationships and online domains where trust must be computed rather than earned. However, classic trust and reputation techniques designed to support computational trust among Internet entities do not meet the scalability requirements and the resource constraints typical of Internet of Things (IoT) devices. This paper provides a general framework for managing computational trust where Blockchain technology and reputation systems are used in conjunction. Our framework relies on a reward-penalty scheme to offer a customizable, secure, and scalable trust architecture for IoT devices and the services they access. We implemented and tested a smart contract-based proof-of-concept, carrying out an analysis of its cost and security to verify the practical viability of our solution.

With the advent of mobile crowd sourcing (MCS) systems and its applications, theselectionof the right crowd is gaining utmost importance. The increasing variability in the context of MCS tasks makes the selection of not only the capable but also the willing workers crucial for a high task completion rate. Most of the existing MCS selection frameworks rely primarily on reputation-based feedback mechanisms to assess the level of commitment of potential workers. Such frameworks select workers having high reputation scores but without any contextual awareness of the workers, at the time of selection, or the task. This may lead to an unfair selection of workers who will not perform the task. Hence, reputation on its own only gives an approximation of workers’ behaviors since it assumes that workers always behave consistently regardless of the situational context. However, following the concept of cross-situational consistency, where people tend to show similar behavior in similar situations and behave differently in disparate ones, this work proposes a novel recruitment system in MCS based on behavioral profiling. The proposed approach uses machine learning to predict the probability of the workers performing a given task, based on their learned behavioral models. Subsequently, a group-based selection mechanism, based on the genetic algorithm, uses these behavioral models in complementation with a reputation-based model to recruit a group of workers that maximizes the quality of recruitment of the tasks. Simulations based on a real-life dataset show that considering human behavior in varying situations improves the quality of recruitment achieved by the tasks and their completion confidence when compared with a benchmark that relies solely on reputation.

Online process mining refers to a class of techniques for analyzing in real-time event streams generated by the execution of business processes. These techniques are crucial in the reactive monitoring of business processes, timely resource allocation and detection/prevention of dysfunctional behavior. Many interesting advances have been made by the research community in recent years, but there is no consensus on the exact set of properties these techniques have to achieve. This article fills the gap by identifying a set of evaluation goals for online process mining and examining their fulfillment in the state of the art. We discuss parameters and techniques regulating the balance between conflicting goals and outline research needed for their improvement. Concept drift detection is crucial in this sense but, as demonstrated by our experiments, it is only partially supported by current solutions.

The popularity of cloud computing services for delivering and accessing infrastructure on demand has significantly increased over the last few years. Concurrently, the usage of FPGAs to accelerate compute-intensive applications has become more widespread in different computational domains due to their ability to achieve high throughput and predictable latency while providing programmability and improved energy efficiency. Computationally intensive applications such as big data analytics, machine learning, and video processing have been accelerated by FPGAs. With the exponential workload increase in data centers, major cloud service providers have made FPGAs and their capabilities available as cloud services. However, enabling FPGAs in the cloud is not a trivial task due to incompatibilities with existing cloud infrastructure and operational challenges related to abstraction, virtualization, partitioning, and security. In this article, we survey recent frameworks for offering FPGA hardware acceleration as a cloud service, classify them based on their virtualization mode, tenancy model, communication interface, software stack, and hardware infrastructure. We further highlight current FPGAaaS trends and identify FPGA resource sharing, security, and microservicing as important areas for future research.

Big data exchange is an emerging problem in the context of big data management and analytics. In big data exchange, multiple entities exchange big datasets beyond the common data integration or data sharing paradigms, mostly in the context of data federation architectures. How to make big data exchange while ensuring privacy preservation constraintsƒ The latter is a critical research challenge that is gaining momentum on the research community, especially due to the wide family of application scenarios where it plays a critical role (e.g., social networks, bio-informatics tools, smart cities systems and applications, and so forth). Inspired by these considerations, in this paper we provide an overview of models and issues in the context of privacy-preserving big data exchange research, along with a selection of future research directions that will play a critical role in next-generation research.

The conflict between the need of protecting and sharing data is hampering the spread of big data applications. Security and privacy assurance is required to protect data owners, while data access and sharing are fundamental to implement smart big data solutions. In this context, access control systems can assume a central role in balancing data protection and data sharing. However, existing access control solutions are not general and scalable enough to address the software and technological complexity of big data ecosystems, being unable to support such a dynamic and collaborative environment. In this paper, we propose an access control system that enforces access to data in a distributed, multi-party big data environment. It is based on data annotations and secure data transformations performed at ingestion time. We show the feasibility of our approach in the smart city domain using an Apache-based big data engine.

Detection of illegal and threatening items in bag-gage is one of the utmost security concern nowadays. Even for experienced security personnel, manual detection is a time-consuming and stressful task.Many academics have created automated frameworks for detecting suspicious and contraband data from X-ray scans of luggage. However, to our knowledge, no framework exists that utilizes temporal baggage X-ray imagery to effectively screen highly concealed and occluded objects which are barely visible even to the naked eye. To address this, we present a novel temporal fusion driven multi-scale residual fashioned encoder-decoder that takes series of consecutive scans as input and fuses them to generate distinct feature representations of the suspicious and non-suspicious baggage content, leading towards a more accurate extraction of the contraband data. The proposed methodology has been thoroughly tested using the publicly accessible GDXray dataset, which is the only dataset containing temporally linked grayscale X-ray scans showcasing extremely concealed contraband data. The proposed framework outperforms its competitors on the GDXray dataset on various metrics.

Summary The advent of the Internet of things (IoT) has radically changed the way in which computations and communications are carried out. People are just becoming another component of IoT environments, and in turn, IoT environments are becoming a mixture of platforms, software, services, things, and people. The price we pay for such dynamic and powerful environment is an intrinsic uncertainty and low trustworthiness due to its opaque perimeter, the multitude of different data sources with unknown providers, and uncertain responsibilities. Trustworthiness of observables collected by smart devices (from minuscle sensors to bigger machines) is fundamental to build a chain of trust on a decision process taken according to these observables. Some assurance solutions evaluate the quality of collected data, although they are difficult to apply in IoT environments for performance and cost reasons. In this paper, we take a different approach and put forward the idea that, in many cases, the behavior of people owning smart devices can contribute to the evaluation of the trustworthiness of collected data and, in turn, of the whole decision process. We therefore define an assurance methodology based on data analytics evaluating the compliance of people to behavioral policies. The more people behavior is compliant, the higher the trustworthiness of data collected through their smart devices.

Summary As now well established, the world population is aging rapidly and, according to World Health Organization (WHO), the amount of people aged 60 years and older is expected to total 2 billion in 2050. For this reason, an emerging important issue is the definition of a new generation of healthcare platforms capable of monitoring people's quality of life. In this article, we propose a new methodology that supports the entire requirement elicitation process starting from the initial phase of gathering the requirements, both clinical, technological, and end‐user, up to the choice of the most suitable solution. Our proposal provides a new new iterative model in the smart healthcare field research area. Furthermore we apply our proposal in a real scenario and we report the end‐to‐end implementation of the proposed methodology.

Internet of Things (IoT) is composed of physical devices, communication networks, and services provided by edge systems and over-the-top applications. IoT connects billions of devices that collect data from the physical environment, which are pre-processed at the edge and then forwarded to processing services at the core of the infrastructure, on top of which cloud-based applications are built and provided to mobile end users. IoT comes with important advantages in terms of applications and added value for its users, making their world smarter and simpler. These advantages, however, are mitigated by the difficulty of guaranteeing IoT trustworthiness, which is still in its infancy. IoT trustworthiness is a must especially in critical domains (e.g., health, transportation) where humans become new components of an IoT system and their life is put at risk by system malfunctioning or breaches. In this article, we put forward the idea that trust in IoT can be boosted if and only if its automation and adaptation processes are based on trustworthy data. We therefore depart from a scenario that considers the quality of a single decision as the main goal of an IoT system and consider the trustworthiness of collected data as a fundamental requirement at the basis of a trustworthy IoT environment. We therefore define a methodology for data collection that filters untrusted data out according to trust rules evaluating the status of the devices collecting data and the collected data themselves. Our approach is based on blockchain and smart contracts and collects data whose trustworthiness and integrity are proven over time. The methodology balances trustworthiness and privacy and is experimentally evaluated in real-world and simulated scenarios using Hyperledger fabric blockchain.

Drone flight controls and ground stations are known to be vulnerable to attacks. Besides posing a threat to integrity and confidentiality of drone data, their vulnerabilities endanger safety. Onboard continuous authentication is a vital countermeasure to hijacking attempts. Motivated by the success of Machine Learning (ML) techniques in the field of behavioral biometrics, this paper investigates the use of sensor readings generated onboard drones and of control data reaching them from the ground to feed an onboard ML model continuously authenticating pilots. We analyze fifteen inertial measurement units (IMU) and four radio control signals obtained from the drone's onboard sensors or coming from its remote controller, to identify the controlling pilot. We investigate three sequence classification schemes. In the first scheme, raw sensor sequences are directly fed to a deep Long/Short-Term Memory (LSTM) learner. In the second scheme, frequency-domain features are extracted from the data sequences and interpreted by an ensemble of random trees. In the third scheme, instantaneous sensor readings are classified using the same ensemble learning technique as in the second scheme, yet a final decision fusion method is adopted to provide a sequence-based decision. We compare the three schemes in terms of accuracy, complexity, and delay. The winning scheme is validated and tested against an unseen intruder scenario. Our tests show that an LSTM model trained with data from 19 users is able to identify the operating user at a 97% accuracy, while it can identify an unknown intruder at an average accuracy of 73%.

Cross-device federated learning (CDFL) systems enable fully decentralized training networks whereby each participating device can act as a model-owner and a model-producer. CDFL systems need to ensure fairness, trustworthiness, and high-quality model availability across all the participants in the underlying training networks. This article presents a blockchain-based framework, TrustFed, for CDFL systems to detect the model poisoning attacks, enable fair training settings, and maintain the participating devices' reputation. TrustFed provides fairness by detecting and removing the attackers from the training distributions. It uses blockchain smart contracts to maintain participating devices' reputations to compel the participants in bringing active and honest model contributions. We implemented the TrustFed using a Python-simulated federated learning framework, blockchain smart contracts, and statistical outlier detection techniques. We tested it over the large-scale industrial Internet of things dataset and multiple attack models. We found that TrustFed produces better results regarding multiple aspects compared with the conventional baseline approaches.

Performance and dependability levels of cloud-based computations are difficult to guarantee by-design due to segregation of visibility and control between applications, data owners, and cloud providers. Lack of predictability increases users' uncertainty about the service levels they will actually achieve. Cloud tenants compete for shared resources/services at all layers of the cloud stack, and pose heterogeneous and conflicting non-functional requirements over them. These requirements have implications for platform and infrastructure layers, which have to be configured to satisfy inter-tenants requirements. We argue that adaptation techniques can play a crucial role in providing a reliable cloud, supporting definite behavior of applications and stable quality of service. Existing adaptation techniques however are unsuitable for cloud use, since they mostly focus on single tenancy, performance requirements, and are based on unverifiable evidence, which is collected in an untrusted way. In this paper, we propose a multi-tenant, general-purpose adaptation technique for the cloud, based on evidence collected by means of a trustworthy certification process. We depart from traditional heavy and comprehensive certification processes, such as ISO/IEC 27017, and consider a flexible and lightweight certification process for the cloud. It is based on authentic evidence and provides accountable validation on the compliance of a cloud-based system. Our approach adapts the cloud at all layers to maintain stable non-functional properties in certificates over time, by continuously verifying certificate validity. We assess the performance and quality of our adaptation approach in a wide range of settings.

The Big Data revolution promises to build a data-driven ecosystem where better decisions are supported by enhanced analytics and data management.However, major hurdles still need to be overcome on the road that leads to commoditization and wide adoption of Big Data Analytics (BDA).Big Data complexity is the first factor hampering the full potential of BDA.The opacity and variety of Big Data technologies and computations, in fact, make BDA a failure prone and resource-intensive process, which requires a trial-and-error approach.This problem is even exacerbated by the fact that current solutions to Big Data application development take a bottom-up approach, where the last technology release drives application development.Selection of the best Big Data platform, as well as of the best pipeline to execute analytics, represents then a deal breaker.In this paper, we propose a return to roots by defining a Model-Driven Engineering (MDE) methodology that supports automation of BDA based on model specification.Our approach lets customers declare requirements to be achieved by an abstract Big Data platform and smart engines deploy the Big Data pipeline carrying out the analytics on a specific instance of such platform.Driven by customers' requirements, our methodology is based on an OWL-S ontology of Big Data services and on a compiler transforming OWL-S service compositions in workflows that can be directly executed on the selected platform.The proposal is experimentally evaluated in a real-world scenario focusing on the threat detection system of SAP.

File carving is a powerful technique for both digital forensics investigations and data recovery. It offers the flexibility to recover data stored on digital media independent of the underlying file system. Thus, it can be used in the cases where we need to recover deleted files or when we have a corrupted, overwritten, or unknown file system. In this paper, we present a novel video file carving (VidCarve) framework to recover and reassemble fragmented video files into playable video files. VidCarve consists of four main components: identification and recovery, weight assignment, reassembly, and file construction. This paper focuses on the weight assignment and reassembly processes where the codec specification parameters of carved fragments were overwritten. We propose several weight assignment techniques to estimate the probability of adjacency between video fragments. Based on these weights, the reassembly algorithm recovers the video files by constructing their correct sequences. We provide experimental results for the proposed techniques of weight assignment and reassembly. We claim that the overall accuracy rate can produce forensically sound evidence and play a critical role in the process of digital evidence recovery in many criminal cases.

Distributed Ledgers (DLs) like Blockchain have become a popular technique to build collective trust in digital records. The rationale is that any agent wishing to append a block to a DL needs to provide proof of holding some property/asset or having performed some costly activity. Thus, “poisoning” a DL with spurious content requires much more effort than poisoning a conventional shared data structure. Based on this idea, DLs are now being deployed as community stores of trusted transaction records, reputation values and even of trustworthy training data for Machine Learning (ML) models. Certainly, when injecting spurious or hostile content in a DL, a rational attacker has to consider whether the damage δ caused by a spurious block B is worth the effort ε needed to append B to the DL; but practical experience has shown that being certain to disrupt a DL-supported application may be a powerful motivator for digital vandalism even when it is costly. In this paper, we put out an alternative idea: Reciprocally Useful Work (RUW), a novel DL update mechanism where any agent wishing to add a block B to the ledger must first perform an activity that will improve the utility for the DL-supported application of some other agent's block B'. We discuss in detail how to apply RUW to DLs storing training data for Machine Learning (ML) models, in order to show that reciprocity can play the role of a direct compensation of the potential disruption, which is measurable in term of the performance of the ML model trained on the DL content.

Distributed ledger technology is envisioned as one of the cornerstones of promising solutions for building the next generation of critical applications.However, there is still quite a bit of confusion and hype around the real security guarantees this technology offers.This is especially due to the fact that for the vast majority of existing blockchain-based consensus protocols it is really hard to find sufficiently detailed documentation that fully captures their behavior.A number of recent papers have formalized the behavior of Bitcoin-like protocols in order to rigorously study the security and privacy properties of their underlying structure, but surprisingly very little work has been devoted to the formalization of distributed ledger systems using BFTlike approaches.In this work, we focus on XRP Ledger, better known as Ripple, and take the first steps towards the complete formalization of its consensus protocol.To this end, we have investigated all the existing documentation and analyzed its source code.We present a formal description of its consensus protocol for every step.Furthermore, we provide an accurate view of its security guarantees in terms of safety and liveness and show how to increase the desired tolerance by changing the value of specific protocol parameters.

Assuring anomaly-free business process executions is a key challenge for many organizations. Traditional techniques address this challenge using prior knowledge about anomalous cases that is seldom available in real-life. In this work, we propose the usage of word2vec encoding and One-Class Classification algorithms to detect anomalies by relying on normal behavior only. We investigated 6 different types of anomalies over 38 real and synthetics event logs, comparing the predictive performance of Support Vector Machine, One-Class Support Vector Machine, and Local Outlier Factor. Results show that our technique is viable for real-life scenarios, overcoming traditional machine learning for a wide variety of settings where only the normal behavior can be labeled.

In this paper, we propose a web-based microservice for programming FPGAs remotely in the cloud without requiring additional hardware or third party software. Docker and Docker-compose are used to implement a scalable, secure environment for FPGA design and operation. The paper further describes in detail the architectural design, user interface, tool flow, and hardware back-end of the FPGA cloud service. The Docker files are made publicly available at GitHub.

The pervasive diffusion of Machine Learning (ML) in many critical domains and application scenarios has revolutionized implementation and working of modern IT systems. The behavior of modern systems often depends on the behavior of ML models, which are treated as black boxes, thus making automated decisions based on inference unpredictable. In this context, there is an increasing need of verifying the non-functional properties of ML models, such as, fairness and privacy, to the aim of providing certified ML-based applications and services. In this paper, we propose a methodology based on Multi-Armed Bandit for evaluating non-functional properties of ML models. Our methodology adopts Thompson sampling, Monte Carlo Simulation, and Value Remaining. An experimental evaluation in a real-world scenario is presented to prove the applicability of our approach in evaluating the fairness of different ML models.

Presents the introductory welcome message from the conference proceedings. May include the conference officers' congratulations to all involved with the conference event and publication of the proceedings record.

The advent of cloud computing has radically changed the concept of distributed environments, where services can now be composed and reused at high rates. Today, service composition in the cloud is driven by the need of providing stable QoS, where non-functional properties of composite services are proven over time and composite services continuously adapt to both functional and non-functional changes of the component services. This scenario introduces substantial costs on the cloud providers that go beyond the cost of deploying component services, and require to consider the costs of continuously verifying non-functional properties of composite and component services. In this paper, we propose a cost-effective approach to certification-based cloud service composition. This approach is based, on one side, on a portable certification process for the cloud evaluating non-functional properties of composite services and, on the other side, on a cost-evaluation methodology aimed to produce the service composition that minimizes the total cost paid by the cloud providers, taking into account both deployment and certification/verification costs. Our service composition approach is driven by certificates awarded to single services and by a fuzzy-based cost evaluation methodology, and assumes certified properties as must-have requirements for service selection and composition.

Traditional assurance solutions for software-based systems rely on static verification techniques and assume continuous availability of trusted third parties. With the advent of cloud computing, these solutions become ineffective since services/applications are flexible, dynamic, and change at runtime, at high rates. Although several assurance approaches have been defined, cloud requires a step-change moving current assurance techniques to fully embrace the cloud peculiarities. In this paper, we provide a rigorous and adaptive assurance technique based on certification, towards the definition of a transparent and trusted cloud ecosystem. It aims to increase the confidence of cloud customers that every piece of the cloud (from its infrastructure to hosted applications) behaves as expected and according to their requirements. We first present a test-based certification scheme proving non-functional properties of cloud-based services. The scheme is driven by non-functional requirements defined by the certification authority and by a model of the service under certification. We then define an automatic approach to verification of consistency between requirements and models, which is at the basis of the chain of trust supported by the certification scheme. We also present a continuous certificate life cycle management process including both certificate issuing and its adaptation to address contextual changes. Finally, we describe our certification framework and an experimental evaluation of its performance, quality, applicability, and practical usability in a real industrial scenario, which considers Engineering Ingegneria Informatica S.p.A. ENGpay online payment system.

This article aims at introducing a new configurable and multipurpose electronic voting service based on the blockchain infrastructure. The objective is to design an architecture to automatically translate service configuration defined by the end user into a cloud-based deployable bundle, automating business logic definition, blockchain configuration, and cloud service provider selection. The article presents the preliminary results of the system and a SOA-based services definition implemented with smart contracts.

The advent of Big Data has revolutionized the way in which data are collected, analyzed, and processed, becoming a pre-requisite for each enterprise that competes in the global market. In this respect, the commodization of Big Data analytics is an essential goal to be faced in the near future. Recently, some preliminary approaches have been presented mostly focusing on distributing Big Data platforms as a service, while less has been done on cross-platform Big Data analytics. In this paper, we propose a model-based methodology for Big Data Analytics-as-a-Service that extends existing techniques by supporting cross-communication between batch and stream processing, deployment on multiple platforms, and end-to-end verification against users' requirements.

Starting from our previous research where we in- troduced a general framework for supporting data-driven privacy-preserving big data management in distributed environments, such as emerging Cloud settings, in this paper we further and significantly extend our past research contributions, and provide several novel contributions that complement our previous work in the investigated research field. Our proposed framework can be viewed as an alternative to classical approaches where the privacy of big data is ensured via security-inspired protocols that check several (protocol) layers in order to achieve the desired privacy. Unfortunately, this injects considerable computational overheads in the overall process, thus introducing relevant challenges to be considered. Our approach instead tries to recognize the “pedigree” of suitable summary data representatives computed on top of the target big data repositories, hence avoiding computational overheads due to protocol checking. We also provide a relevant realization of the framework above, the so- called Data-dRIven aggregate-PROvenance privacy-preserving big Multidimensional data (DRIPROM) framework, which specifically considers multidimensional data as the case of interest. Extensions and discussion on main motivations and principles of our proposed research, two relevant case studies that clearly state the need-for and covered (related) properties of supporting privacy- preserving management and analytics of big data in modern distributed systems, and an experimental assessment and analysis of our proposed DRIPROM framework are the major results of this paper.

The cloud paradigm has revolutionized the way in which software systems are designed, managed, and maintained. With the advent of the microservice architecture, this trend was brought to the extreme, pushing the whole software development process towards unification of software development (Dev) and software operation (Ops). This rapid evolution has not immediately found counterparts in assurance techniques, where the evaluation of the non-functional behavior of a software system and of the software development process are completely decoupled. In this paper, we put forward the idea that next-generation assurance techniques, and more specifically certification techniques, must evaluate a software system throughout the whole development process. To this aim, we define a continuous certification scheme for DevOps that evaluates the software artifacts produced at each stage of the development process. We then present the assurance framework managing our certification scheme and experimentally evaluate the continuous certification scheme in a real DevOps scenario.

The Internet of Things (IoT) smart devices enable many applications, such as smart energy, traffic control, water management and environmental sensing in a smart city environment. It provides the end users (individuals and enterprises) the convenience and improved computational and communication capabilities between two devices. Yet the IoT technology is accompanied by security challenges that must be addressed in order to ensure the security and privacy of the network among multiple devices. This is done by using schemes and mechanisms which accommodate the heterogeneous nature of the IoT devices environment, and the resource-constrained nature of some of its components. There have been many efforts to develop authentication protocols such as TESLA protocol. TESLA is a source authentication protocol for the broadcast network. TESLA addresses these challenges, yet it suffers from limitations to its utility and security for IoT environments. The proposed protocol-based TESLA is designed to provide lower computation against a DoS attack. The proposed scheme is using a combination of Multilevel-μTESLA and Inf-TESLA protocols. The benefit of integration between two protocols is to reduce the delay between the sender and the receiver, allows continues authenticating of the message and increasing resistance to DoS attacks. We analysis and discuss in details out proposed protocol TLI- μTESLA.

A lot of people in Japan suffer from bad conditions of their mental health with an increasing tendency, in particular jobseekers and elderly persons. The classical way to solve their problem is to consult a counselor, who treats these people in a way to become aware of the core of their problem and to solve it. However, the number of well qualified counselors is limited. For this purpose, we developed a VCA (Virtual Counseling Agent) as a further evolution of a formerly developed CRECA (Context Respectful Counseling Agent). CRECA had a text interface. To much more imitate a human counselor, VCA has an image avatar and a voice conversation using the Google Cloud audio API. Further, VCA is made independent of counseling content fields. Thus, it is more generalized than CRECA or ELIZA in order for every people to easily use everywhere in every situation. Here, VCA, CRECA, and ELIZA are comparatively evaluated by questionnaire after the use of 10 college students having career problems as well as elderly persons struggling with modern IT. As a result, VCA significantly exceeded the average value of ELIZA along with the significant difference at the level of 5%. Moreover, average of the evaluation value is not worse than CRECA. Compared to CRECA, VCA does not limit the content and field of consultation. Especially, elderly persons struggling with modern IT could not use CRECA that have only text interface. It can be used generally at any time in everyday natural conversation. It can easily be used by elderly people and the digital divided due to voice conversion.

Spam has become the platform of choice used by cyber-criminals to spread malicious payloads such as viruses and trojans. In this paper, we consider the problem of early detection of spam campaigns. Collaborative spam detection techniques can deal with large scale e-mail data contributed by multiple sources; however, they have the well-known problem of requiring disclosure of e-mail content. Distance-preserving hashes are one of the common solutions used for preserving the privacy of e-mail content while enabling message classification for spam detection. However, distance-preserving hashes are not scalable, thus making large-scale collaborative solutions difficult to implement. As a solution, we propose Spamdoop, a Big Data privacy-preserving collaborative spam detection platform built on top of a standard Map Reduce facility. Spamdoop uses a highly parallel encoding technique that enables the detection of spam campaigns in competitive times. We evaluate our system's performance using a huge synthetic spam base and show that our technique performs favorably against the creation and delivery overhead of current spam generation tools.

A challenge in designing cooperative distributed systems is to develop feasible and cost-effective mechanisms to foster cooperation among selfish nodes, i.e., nodes that strategically deviate from the intended specification to increase their individual utility. Finding a satisfactory solution to this challenge may be complicated by the intrinsic characteristics of each system, as well as by the particular objectives set by the system designer. Our previous work addressed this challenge by proposing RACOON, a general and semi-automatic framework for designing selfishness-resilient cooperative systems. RACOON relies on classical game theory and a custom built simulator to predict the impact of a fixed set of selfish behaviours on the designer's objectives. In this paper, we present RACOON++, which extends the previous framework with a declarative model for defining the utility function and the static behaviour of selfish nodes, along with a new model for reasoning on the dynamic interactions of nodes, based on evolutionary game theory. We illustrate the benefits of using RACOON++ by designing three cooperative systems: a peer-to-peer live streaming system, a load balancing protocol, and an anonymous communication system. Extensive experimental results using the state-of-the-art PeerSim simulator verify that the systems designed using RACOON++ achieve both selfishness-resilience and high performance.

The diffusion of service-based and cloud-based systems has created a scenario where software is often made available as services, offered as commodities over corporate networks or the global net. This scenario supports the definition of business processes as composite services, which are implemented via either static or runtime composition of offerings provided by different suppliers. Fast and accurate evaluation of services’ security properties becomes then a fundamental requirement and is nowadays part of the software development process. In this article, we show how the verification of security properties of composite services can be handled by test-based security certification and built to be effective and efficient in dynamic composition scenarios. Our approach builds on existing security certification schemes for monolithic services and extends them towards service compositions. It virtually certifies composite services, starting from certificates awarded to the component services. We describe three heuristic algorithms for generating runtime test-based evidence of the composite service holding the properties. These algorithms are compared with the corresponding exhaustive algorithm to evaluate their quality and performance. We also evaluate the proposed approach in a real-world industrial scenario, which considers ENGpay online payment system of Engineering Ingegneria Informatica S.p.A. The proposed industrial evaluation presents the utility and generality of the proposed approach by showing how certification results can be used as a basis to establish compliance to Payment Card Industry Data Security Standard.

Inner-product encryption (IPE) is a well-known functional encryption primitive that allows decryption when the inner-product of the attribute vectors, upon which the encrypted data and the decryption key depend, is equal to zero. Using IPE, it is possible to define fine-grained access policies over encrypted data whose enforcement can be outsourced to the cloud where the data are stored. However, current IPE schemes do not support efficient access policy changes. In this paper, we propose an efficient inner-product proxy re-encryption (E-IPPRE) scheme that provides the proxy server with a transformation key, with which a ciphertext associated with an attribute vector can be transformed to a new ciphertext associated with a different attribute vector, providing a policy update mechanism with a performance suitable for many practical applications. We experimentally assess the efficiency of our protocol and show that it is selective attribute-secure against chosen-plaintext attacks in the standard model under the Asymmetric Decisional Bilinear Diffie-Hellman assumption.

This paper introduces a general framework for supporting data-driven privacy-preserving big data management in distributed environments, such as emerging Cloud settings. The proposed framework can be viewed as an alternative to classical approaches where the privacy of big data is ensured via security-inspired protocols that check several (protocol) layers in order to achieve the desired privacy. Unfortunately, this injects considerable computational overheads in the overall process, thus introducing relevant challenges to be considered. Our approach instead tries to recognize the "pedigree" of suitable summary data representatives computed on top of the target big data repositories, hence avoiding computational overheads due to protocol checking. We also provide a relevant realization of the framework above, the so-called Data-dRIven aggregate-PROvenance privacypreserving big Multidimensional data (DRIPROM) framework, which specifically considers multidimensional data as the case of interest.

Cybersecurity is the second emergency in Europe just after the climate changes. Everyday most of the small, medium and big enterprises are under attack. This scenario requires, on one side, new security solutions protecting ICT systems against misbehaviors/malicious attacks and, on the other side, a continuous assurance process evaluating the system robustness against new threats. In this paper we present Moon Cloud, a Cloud PaaS solution providing customizable assurance based on compliance for ICT systems, including public and private cloud systems and IoT environments. We also present a concrete security assessment carried out in a real scenario.

In IoT environments, data are collected by many distinct devices, at the periphery, so that their feature-sets can be naturally endowed with a faceted structure. In this work, we argue that the IoT requires specialized ML models, able to exploit this faceted structure in the learning strategy. We demonstrate the application of this principle, by a multiple kernel learning approach, based on the exploration of the partition lattice driven by the natural partitioning of the feature set. Furthermore, we consider that the whole data management, acquisition, pre-processing and analytics pipeline results from the composition of processes pursuing different and non-perfectly aligned goals (most often, enacted by distinct agents with different constraints, requirements competencies and with non-aligned interests). We propose the adoption of an adversarial modeling paradigm across the overall pipeline. We argue that knowledge of the composite nature of the learning process, as well as of the adversarial character of the relationship among phases, can help in developing heuristics for improving the learning algorithms efficiency and accuracy. We develop our argument with reference to few exemplary use cases.

Blockchain technology is having a deep impact on the financial and technical sectors providing a mechanism for the creation of decentralized currencies and a number of applications in different fields.At the core of the technology there is a consensus protocol enabling the maintenance of a distributed ledger.In general current systems are complex schemes that implement a combination of cryptographic algorithm, distributed techniques, and incentive driven behaviour.In this paper we focus on three of the most diffused platforms, i.e.Bitcoin, Ripple, and Ethereum, and provide a comparative analysis of their most important features such as the architecture, the scripting language, the economic and security properties.

A lot of IT personnel have psychological distress and counselors to help them are lack in number. Therefore, we proposed a counseling agent (CA) called CRECA (context respectful counseling agent), which listens to clients and promotes their reflection context respectfully namely in a context preserving way. This agent is now enhanced using a body language called "unazuki" in Japanese, a kind of nodding to greatly promote dialogue, often accompanying "un-un" (meaning "exactly") of Japanese onomatopoeia. This body language significantly helps represent empathy or entire approval. Our agent is enhanced with such dialog promotion nodding robot to continue the conversation naturally or context respectfully towards clients' further reflection. To realize it, the robot nods twice at each end of dialog sentence input by clients. Here, we introduce a robot that behaves human-like by an appropriate nodding behavior. The motivation for such a more human-like robot was the extension of application fields from IT workers' counselling to people, who suffer from more social problems such as financial debt, or anxiety of victory or defeat. For such applications, it is important that the agent behaves as much as possible human-like. Here, we present an enhanced experimental evaluation. The quantitative evaluation is based on the utterance amounts of a test group of individuals. These amount with and without the nodding feature are compared. Additionally, the robots with and without nodding are compared.

Analysis of interactions with remotely controlled devices has been used to detect the onset of hijacking attacks, as well as for forensics analysis, e.g., to identify the human controller. Its effectiveness is known to depend on the remote device type as well as on the properties of the remote control signal. This paper shows that the radio control signal sent to an unmanned aerial vehicle (UAV) using a typical transmitter can be captured and analyzed to identify the controlling pilot using machine learning techniques. Twenty trained pilots have been asked to fly a high-end research drone through three different trajectories. Control data have been collected and used to train multiple classifiers. Best performance has been achieved by a random forest classifier that achieved accuracy around 90% using simple time-domain features. Extensive tests have shown that the classification accuracy depends on the flight trajectory and that the pitch, roll, yaw, and thrust control signals show different levels of significance for pilot identification. This result paves the way to a number of security and forensics applications, including continuous identification of UAV pilots to mitigate the risk of hijacking.

The cloud computing paradigm entails a radical change in IT provisioning, which must be understood and correctly applied especially when security requirements are considered. Security requirements do not cover anymore just the application itself, but involve the whole cloud supply chain from the hosting infrastructure to the final applications. This scenario requires, on one side, new security mechanisms protecting the cloud against misbehaviors/malicious attacks and, on the other side, a continuous and adaptive assurance process evaluating the observed cloud security behavior against the expected one. In this paper, we focus on the evaluation of the security assurance of OpenStack, a major open source cloud infrastructure. We first define a security benchmark for OpenStack, inspired by Center for Internet Security (CIS) benchmark for cloud infrastructures. We then present a platform, called Moon Cloud, for cloud security assurance evaluation, showing an application of our benchmark and platform to the in-production OpenStack deployment of the University of Milan.

Secure Multi-party Computation (SMC) has been introduced to allow the computation of generic functions between two parties that want to keep secret the input they use, and share only the computed result. One of the approach proposed to solve the SMC problem relies on the design of Garbled Circuits (GC), that are Boolean circuits that can be evaluated collaboratively achieving the SMC goal. Recently, there is a growing interest on the efficiency of this technique and on its potential applications to computation outsourcing in untrusted environments. One of the possible ways to reduce the complexity of the computation is to lower the number of non-EXOR gates in the Boolean circuit, since those gates have no cost for the execution of the secure computation protocol. In this work, we discuss the possibility to construct Garbled Circuit using quantum gates (QG), observing that, in some cases, the quantum GC requires a lower number of non-EXOR gates with respect to the corresponding classical GC implementations, thus improving the overall efficiency of the execution of the SMC protocol.

Selfishness is one of the key problems that confronts developers of cooperative distributed systems (e.g., file-sharing networks, voluntary computing). It has the potential to severely degrade system performance and to lead to instability and failures. Current techniques for understanding the impact of selfish behaviours and designing effective countermeasures remain manual and time-consuming, requiring multi-domain expertise. To overcome these difficulties, we propose SEINE, a simulation framework for rapid modelling and evaluation of selfish behaviours in a cooperative system. SEINE relies on a domain-specific language (SEINE-L) for specifying selfishness scenarios, and provides semi-automatic support for their implementation and study in a state-of-the-art simulator. We show in this paper that (1) SEINE-L is expressive enough to specify fifteen selfishness scenarios taken from the literature, (2) SEINE is accurate in predicting the impact of selfishness compared to real experiments, and (3) SEINE substantially reduces the development effort compared to traditional manual approaches.

Human life can be seriously affected by unusual high solar flare. It causes serious problems such as destroying satellites, damaging electric power plants, etc. Predicting solar flare peaks is indispensable. Support Vector Machine (SVM) was used to predict the solar flare intensity based on data of the past. However, such prediction is an extremely difficult imbalanced classification problem causing a very large scale combinatorial problem. To overcome this, a local optimizer such as SVM was cooperatively or synergistically integrated with a case base and GA. This extension was called Case Based Genetic Algorithm with Local Optimizer (CBGALO). This synergetic technology outperformed around 10% over SVM only. However, GA is known for a tendency to fall into stagnation or local optima without improving. This paper presents a further extended strategy which introduces GA restarting with various operations such as mutation rate etc. especially with various but high quality cases used as the initial population at each restart. This highly synergetic technology is called CBRSGALO (Case Based integration of ReStart GA with Local Optimizer). Experimental evaluation showed that CBRSGALO outperformed around 20% over just a local optimizer such as SVM.

Nowadays, a lot of IT personnel have psychological distress. Meanwhile, counselors to help them are lack in number. To solve the problem, we proposed a counseling agent (CA) called CRECA (context respectful counseling agent). CRECA listens to clients and promotes their reflection context respectfully namely in a context preserving way. This agent can be enhanced using a body language called "unazuki" in Japanese, a kind of "nodding" to greatly promote dialogue, often accompanying "un-un" (meaning "exactly") of Japanese onomatopoeia. This body language is expected to significantly help represent empathy or entire approval. In this paper, the agent is integrated with such a "unazuki" or "dialog promotion nodding" robot to continue the conversation naturally or context respectfully towards clients' further reflection. To realize such "unazuki", the robot nods twice at each end of dialog sentence input by clients. The experimental evaluation proves such nodding is effective in counseling.

Secure Multi-party Computation (SMC) protocols enable two or more parties to compute collaboratively generic functions while keeping secret their inputs, sharing only the final result. To achieve this goal, a technique relying on the design of Garbled Circuits (GC) has been firstly proposed by Yao. Garbled circuits are Boolean circuits that can be evaluated using a distributed protocol for computing the result for each gate, till computing the output values. To improve the efficiency of this technique and exploit SMC protocols in practical applications, such as computation outsourcing in untrusted environments, a number of optimizations have been introduced. In this paper we analyze the deployment of Multiple Valued Logic techniques for the design of GC, discussing their impact on the overall computation and communication costs.

The Big Data and Data Analytics is a brand new paradigm, for the integration of Internet Technology in the human and machine context. For the first time in the history of the human mankind we are able to transforming raw data that are massively produced by humans and machines in to knowledge and wisdom capable of supporting smart decision making, innovative services, new business models, innovation, and entrepreneurship. For the Web Science research, this is a new methodological and technological spectrum of advanced methods, frameworks and functionalities never experienced in the past. At the same moment communities out of web science need to realize the potential of this new paradigm with the support of new sound business models and a critical shift in the perception of decision making. In this short visioning article, the authors are analyzing the main aspects of Big Data and Data Analytics Research and they provide their own metaphor for the next years. A number of research directions are outlined as well as a new roadmap towards the evolution of Big Data to Smart Decisions and Cognitive Computing. The authors do hope that the readers would like to react and to propose their own value propositions for the domain initiating a scientific dialogue beyond self-fulfilled expectations.

Mobile agents are smart programs that migrate from one platform to another to perform the user task. Mobile agents offer flexibility and performance enhancements to systems and service real-time applications. However, security in mobile agent systems is a great concern. In this paper, we propose a novel Broadcast based Secure Mobile Agent Protocol (BROSMAP) for distributed service applications that provides mutual authentication, authorization, accountability, nonrepudiation, integrity, and confidentiality. The proposed system also provides protection from man in the middle, replay, repudiation, and modification attacks. We proved the efficiency of the proposed protocol through formal verification with Scyther verification tool.

Connected Communities (CCs) are socio-technical systems that rely on an information and communication technology (ICT) infrastructure to integrate people and organizations (companies, schools, hospitals, universities, local and national government agencies) willing to share information and perform joint decision-making to create sustainable and equitable work and living environments. We discuss a research agenda considering CCs from three distinct but complementary points of view: CC metaphors, models, and services.

Smart home is one of the most popular IoT (Internet of Things) applications, which connects a wide variety of objects and home appliances in a single logical network. Smart home applications have benefited from interactions and data transmissions among different devices over the integrated network with or without human interventions. However, like other technologies, smart home likely introduces new security vulnerabilities due to its dynamic and open nature of connectivity with heterogeneous features. Among such vulnerabilities, is the breach of confidentiality which needs to be addressed urgently as data exchanged between smart home devices can contain crucial information related to user's privacy and safety. However, some of the challenges in providing smart home system with confidentiality service are the flexibility of key management and efficiency of computation and communication. These challenges should be addressed carefully as many small and resource-constrained devices are usually involved in smart home systems. In this paper, we address these challenges by proposing a lightweight encryption scheme for smart homes. This scheme will provide users and smart objects with confidentiality service without incurring much overhead cost associated with computation and communication. Our proposed scheme also supports flexible public key management through adopting identity-based encryption, which does not require complex certificate handling. We provide a formal security analysis of our scheme and a performance simulation study. The simulation shows that our scheme provides favorable level of efficiency in terms of overhead cost associated with computation and communication.

Big Data domain is one of the most promising ICT sectors with substantial expectations both on the side of market growing and design shift in the area of data storage managment and analytics. However, today, the level of complexity achieved and the lack of standardisation of Big Data management architectures represent a huge barrier towards the adoption and execution of analytics especially for those organizations and SMEs not including a sufficient amount of competences and knowledge. The full potential of Big Data Analytics (BDA) can be unleashed only through the definition of approaches that accomplish Big Data users' expectations and requirements, also when the latter are fuzzy and ambiguous. Under these premises, we propose Big Data Analytics-as-a-Service (BDAaaS) as the next-generation Big Data Analytics paradigm and we discuss issues and challenges from the BDAaaS design and development perspective.

In this study we analyzed the curricula of 65 university students to investigate the impact of activities progression on student performances. Clustering curricula based on activity order and type we discovered a significant incidence on performance, validating the predictive power of curricula. Nevertheless, we discovered that the characterization of clusters is mainly due to non mandatory activities, selected by a student to personalize his curriculum, while activity order is very less relevant. This observation rejects the idea that activities progression has impact on performance, resulting rather as a consequence of student choices.

A lot of IT workers suffer from stress in doing their work and there are a few counselors to help them. To cope with this problem, an enhanced context respectful counseling agent is proposed. This counseling agent extracts emotional words from clients' utterances throughout their dialogue to detect their changes and provides clients with such changes as dialogue summary. If no change is detected, it replies with clients' utterances' paraphrases followed by context-respectful prompts to dig/ narrow problems. Especially to continue the conversation towards clients' further reflection, our newly enhanced agent restricts or relates the topics with eventual and emotional words in dialogue sentences. Namely, it asks still context-respectful but self-disclosure type questions to understand the distressed client more correctly or more sincerely. Furthermore, it uses fuzzy reasoning to select an non boring response either from several digging prompts such as “more concretely”, “say more”, “please say it in detail”, etc. or from several sentences in case of no matching of input utterance with the above mentioned paraphrasing patterns. Owing to this enhancement, clients keeping and deepening reflection on themselves without boring in conversation, reach more problem clarification and self-awareness, which enables them to solve their more difficult problems.

Virtual reality technologies and their applications have received increasing attention in recent years from various perspectives. The thriving numbers behind their adoption and exploitation for dif...

Demosaicking is a digital image process to reconstruct full color digital images from incomplete color samples from an image sensor. It is an unavoidable process for many devices incorporating camera sensor (e.g., mobile phones, tablet, and so on). In this paper, we introduce a new demosaicking algorithm based on polynomial interpolation-based demosaicking. Our method makes three contributions: calculation of error predictors, edge classification based on color differences, and a refinement stage using a weighted sum strategy. Our new predictors are generated on the basis of on the polynomial interpolation, and can be used as a sound alternative to other predictors obtained by bilinear or Laplacian interpolation. In this paper, we show how our predictors can be combined according to the proposed edge classifier. After populating three color channels, a refinement stage is applied to enhance the image quality and reduce demosaicking artifacts. Our experimental results show that the proposed method substantially improves over the existing demosaicking methods in terms of objective performance (CPSNR, S-CIELAB ΔE*, and FSIM), and visual performance.

The business potential of big data is leading to a data-driven economy, where low-cost and low-latency data analysis represents a major competitive advantage. The research community has proposed many technological solutions for big data, such as NoSQL databases, which are difficult to evaluate and compare via standard IT procurement procedures. In addition, lack of competences in big data domains make procurement of big data solutions a tedious and uncertain process, which might impair the success of a business. In this paper, we present a score-based benchmark for distributed databases, which supports adopters in selecting a solution that fits their needs. The proposed benchmark is independent from the configurations of the specific database and deployment environment, requires low effort on the part of end users, is extensible and can be applied to both SQL and NoSQL databases, can be used to evaluate databases according to different properties (e.g., performance, consistency), and can be integrated with existing benchmarks to reduce the burden of their execution. We experimentally evaluate our methodology to validate its effectiveness.

Data security is one of the main concerns organizations have when implementing cloud computing. In particular, data leakage issues in public clouds have been widely studied. Data remanence is considered a major threat, as residual data may include sensitive information like user names, passwords, encryption keys, URLS, etc. However, until now little if any experimental evidence has been put forward supporting the existence and extent of such threat in commercial cloud VMs. In this paper, we provide experimental proof of the remanence of data in VM memory and hard disk. Our experimental design is repeatable and suitable for inclusion in assurance testing and certification suites.

Cloud users and service providers are increasingly concerned about the management of their data and the behavior of the applications they use/own once stored/deployed in the cloud. They therefore ask for enhanced assurance solutions, which partially mitigate the new risks and threats they are facing. Among existing solutions, certification has been widely adopted as a preferable approach to increase trust in the cloud. In this paper, after briefly discussing our test-based certification scheme for the cloud, we show a real certification process aimed to certify Open Stack, an open source IaaS solution for managing infrastructure resources. In particular, we first describe the testing activities executed to certify Open Stack for security and performance properties. We then illustrate the obtained results and the outcomes of the certification process.

A common feature provided by any Cloud Service Provider (CSP) is their library of pre-built and ready to use operating system images that contribute to the overall flexibility, usability and cost savings advantages of Cloud Computing. The pedigree of CSP library images can vary, and some concerns have been raised about confidentiality of user historical data via publicly available images which have not been prepared in a manner consistent with recommended security best practices. In this paper we explore data remanence security concerns associated with virtual machine (VM) instances templates, a popular technique for configuring VMs for new users. We show how forensics tools can be used to check for data remanence and how to appropriately deconflict findings for improved assurance.

The advent of social networks and Internet-of-Things has resulted in unprecedented capability of collecting, sharing and analyzing massive amounts of data. From a security perspective, Big Data may seriously weaken confidentiality, as techniques for improving Big Data analytics performance-including early fusion of heterogeneous data sources - increase the hidden redundancy of data representation, generating ill-protected copies. This gray area of redundancy triggers new disclosure threats that challenge traditional techniques to protect privacy and confidentiality. This position paper starts by proposing a definition of the Big Data Leak threat (as opposed to the one of data breach) and its role as a component of disclosure risk. Then, it discusses how a paradigm of Known, Detect, Contain and Recover could be used to establish Big Data security practices for containing disclosure risks connected to Big Data analytics.

Sequential, predominantly temporal nature of the vast amounts of big data released every day from many different sources could potentially be linked, aligned along the time and deliver new evidence for the next generation predictive systems or knowledge discovery engines. However, big data owners are reluctant to share their data due to legally binding privacy and identity protection concerns, thereby posing a major hurdle preventing shared exploitation of big data on a massive scale. Data anonymization is expected to solve this problem, yet the current approaches are limited predominantly to univariate time series generalized by aggregation or clustering to eliminate identifiable uniqueness of individual data points or patterns. For multivariate time series, uniqueness among of the combination of values or patterns across multiple dimensions is much harder to eliminate due the to exponentially growing number of unique configurations of point values across multiple dimensions. Our method implements linearly scalable asynchronous summarization of multivariate time series independently at every dimension. As a result the series retain only a small subset of defining points at different times along multiple dimensions effectively breaking up the multivariate time series into a collection of summarized univariate time series that are perturbed from the original series in terms of actual points and pattern shapes. Current implementation of the anonymizing summarization involves shape preserving greedy elimination and aggregation that supports parallel cluster processing for big data implementation.

This work adresses the problem estimating correlations between process observables and KPI/SLA violation metrics. This analysis is aimed at providing business process owners with a suggestion of potential causality between groups of process parameters and violations. Obviously, static regression analysis cannot establish causality. We introduce a notion of Behavioral Analysis of business process instances and argue that, under suitable assumptions, Granger correlation can be used to highlight potential causality between business process observables and violations of leading KPIs. To handle the combinatorial explosion of the process observables search space, we describe a game theoretical approach for identifying (sets of) time-shifted process attributes to be tested.

A data owner outsourcing the database of a multi user application wants to prevent information leaks caused by outside attackers exploiting software vulnerabilities or by curious personnel. Query processing over encrypted data solves this problem for a single user, but provides only limited functionality in the face of access restrictions for multiple users and keys. ENKI is a system for securely executing queries over sensitive, access restricted data on an outsourced database. It introduces an encryption based access control model and techniques for query execution over encrypted, access restricted data on the database with only a few cases requiring computations on the client. A prototype of ENKI supports all queries seen in three real world use cases and executes queries from TPC-C benchmark with a modest overhead compared to the single user mode.

It is common to operate an IT system where client computers in offices in a country access cloud computers in another country via the Internet. However, in some countries including China, network communication is often shut down by governmental bodies, in addition to network outage caused by network attacks. In case of such intentional interruptions, users need countermeasures to avoid them. Here, we propose a method to form bypass routes which consist of application-level gateways and intelligent routers placed at offices where client computers run, to select bypass routes based on the Internet status. A method for applying asymmetric criteria to decide whether to apply bypass routes is proposed for robust operation of Internet based applications. Differential values of network latency are used for detecting intentional barriers through monitoring and analyzing the huge amount of temporal data, and absolute values to determine their ends. Such temporal data analysis knowledge is verified by a network simulator.

A challenge in designing a peer-to-peer (P2P) system is to ensure that the system is able to tolerate selfish nodes that strategically deviate from their specification whenever doing so is convenient. In this paper, we propose RACOON, a framework for the design of P2P systems that are resilient to selfish behaviours. While most existing solutions target specific systems or types of selfishness, RACOON proposes a generic and semi-automatic approach that achieves robust and reusable results. Also, RACOON supports the system designer in the performance-oriented tuning of the system, by proposing a novel approach that combines Game Theory and simulations. We illustrate the benefits of using RACOON by designing two P2P systems: a live streaming and an anonymous communication system. In simulations and a real deployment of the two applications on a testbed comprising 100 nodes, the systems designed using RACOON achieve both resilience to selfish nodes and high performance.

In this paper, we investigate privacy-preserving query processing (P3Q) techniques on partitioned databases, where relational queries have to be executed on horizontal data partitions held by different data owners. In our scenario, data owners use Secure Multi-party Computation (SMC) to compute privacy-preserving queries on entire relation(s) without sharing their private partitions. Our solution is applicable to a subset of SQL query language called SQL−− including selection and equi-join queries. To nicely scale up with large size data, we show that computation and communication costs can be reduced via a novel bucketization technique. We consider the classical notion of query privacy, where the querier only learns query results (and what can be inferred from it), and data owners learn as little as possible (in a computational sense) about the query. To ensure such privacy, our technique involves a trusted party only at the beginning of the protocol execution. Experimental results on horizontally partitioned, distributed data show the effectiveness of our approach.

As more and more companies are embracing Big data, it has become apparent that the ultimate challenge is to relate massive amounts of event data to processes that are highly dynamic. To unleash the value of event data, events need to be tightly connected to the control and management of operational processes. However, the primary focus of Big data technologies is currently on storage, processing, and rather simple analytical tasks. Big data initiatives rarely focus on the improvement of end-to-end processes. To address this mismatch, we advocate a better integration of data science, data technology and process science. Data science approaches tend to be process agonistic whereas process science approaches tend to be model-driven without considering the “evidence” hidden in the data. Process mining aims to bridge this gap. This editorial discusses the interplay between data science and process science and relates process mining to Big data technologies, service orientation, and cloud computing.

The success of cloud computing has radically changed the way in which services are implemented and deployed, and made accessible to external and remote users. The cloud computing paradigm, in fact, supports a vision of distributed IT where software services and applications are outsourced and used on a pay-as-you-go basis. In this context, the ability to guarantee an effective management of cloud performance and to support automatic scalability become fundamental requirements. Cloud users are increasingly interested in a transparent and coherent vision of cloud, where performance is guaranteed in different scenarios, and under different and heterogeneous loads. In this paper, we analyze the benefits of an integrated scalability approach at different layers of the cloud stack, focusing on the computing infrastructure and database layers. To this aim, we provide different performance metrics and a set of rules based on them to evaluate the status of the cloud stack and scale it on demand to maintain stable performance. We then implement a proof-of-concept architecture to experimentally analyze cloud performance in three scenarios of scalability: computing infrastructure only, database only, and the case in which computing infrastructure and database compete for resources.

Welcome to the 4th IEEE 2014 Services Workshop on Security and Privacy Engineering (SPE 2014), June 28, 2014, Anchorage, Alaska, USA. SPE 2014 is co-located with IEEE 10th World Congress on Services (IEEE SERVICES 2014).

A lot of IT workers suffer from stress in doing their work and there are a few counselors to help them. To cope with this problem, an emotional word focused context respectful counseling agent is proposed. This counseling agent extracts emotional words from clients' utterances throughout their dialogue to detect their changes and provides clients with such changes as dialogue summary. If no change is detected, it replies with clients' utterances' paraphrases followed by context-respectful prompts to dig/ narrow problems. This way, the counseling agent can pretend to keep recognizing clients' psychological sufferings as contexts or situations. It behaves as if it empathized with clients and continues talking to clients without losing their trust. Keeping reflection on themselves, clients reach more problem clarification and self-awareness, which enables them to solve their problems. Since the agent provides only the information on clients' sayings and the summaries focused on the change in their emotions, there occur few problems of knowledge explosion and knowledge maintenance. Python was used for implementing this agent. The effect on the counseling was experimentally evaluated.

Streaming video has recently surpassed peer-to-peer networks in terms of network capacity hunger.Reports estimate a share of 40 % of peak network capacity dedicated to entertainment, mostly streaming video.A large share of this traffic originates from web-based services.YouTube alone takes up to 8 % of the prime time Internet traffic.While transmission currently works in a best effort system, multimedia information systems on the web are far from being perfect.Retrieval, annotation, validated and useful metadata, reliable and trusted services, and user interaction and context-based adaptation are still under discussion and issues to research.Currently, the Web itself faces dramatic changes, looking for example at the spread of social networks, like Facebook, Twitter or the YouTube community, which become part of everyday life of more and more people.Technologies like Linked Data, HTML5, WebM, or WebRTC are enablers that make these changes possible and let people experience the Web without knowing details about technology.Also the availability of the Web has changed a lot.Many people create multimedia data on the go, put videos and photos on microblogs, or share audiovisual data with their loved ones or colleagues.These activities also have a deep effect on multimedia data formats and usage, multimedia systems and multimedia service providers."Multimedia everywhere" was a common concept before, but this has changed to "relevant media at your finger tips", so new methods for finding, annotating, sharing, remixing, summarizing, transmitting, storing and consuming multimedia data have to be found.

Accurate and lightweight evaluation of web service security properties is a key problem, especially when business processes are dynamically built by composing atomic services provided by different suppliers at runtime. In this paper, we tackle this problem by proposing a security certification approach that virtually certifies a composite service for a set of security properties, starting from certificates awarded to the component services.

An Agent Based Model is proposed to study the individual and collective behavioral changes toward environmental sustainability using ICT-based services. Using ABMs to simulate how environmental awareness spreads is an interdisciplinary issue that involves ICT and energy and environment studies, as well as social and behavioral sciences. Our demonstration will show how the proposed ABM can describe the impact of such awareness on consumption of a limited or critical resource, like energy or water. We will show that there are scenarios that lead to overuse of the resource and scenarios in which this does not happen because sustainable behavior emerges. The key discriminating factor is the collective situational awareness of environmental effects of actions. Such awareness makes "green behavior" easier and can counter possible rebound effects. The demonstration will focus on the role played by smart metering functions.

In online business, it is important to launch sale campaigns for popular products in order to improve page access as well as purchase rates. Online shop owners need to hold campaign sales frequently throughout the year to keep customers coming back. Also, online sales campaigns have to adapt to external circumstances such as customers' needs and the surrounding economic situations. To cope with these requirements, we propose an adaptive system for automatically generating online sales campaigns. In this system, sale products, their price, etc. are automatically adjusted, using knowledge or information acquired by being aware of users' needs such as discount request, product stock, product popularity, and so on. Thus campaign sales pages are semi-automatically organized, interacting with shop owners via a management page and a visual editor. Our system is ready to use heterogeneous data sources, including monitoring/mining the data of user's behavior such as eye gaze as well as economical and/or past sale data.

The need of a certification process for cloud-based services is emerging as a way to address some of the remaining obstacles facing the effective development and diffusion of the cloud-computing paradigm. In this paper we move the first steps towards a complete approach containing a conceptual framework where the specifications of basic, hybrid and incremental certification models for cloud-based services can be given. Specifically, we focus on the definition of a unifying meta-model to provide representational guidelines for (i) the definition of the security properties to be certified, (ii) the types of evidence underlying them, (iii) the phases of the certificate life cycle, as well as of all mechanisms for generating supporting evidence.

In this paper we propose a new architecture and methodology to define a collaborative environment aimed at supporting the innovation process. In the first part of this paper we analyse the data collected during an experiment for testing a collaborative environment and, in the second part, we propose an architecture to support and stimulate innovation processes. Our solution is based on three components, namely a (i) collaborative platform, (ii) a tool able to extract knowledge from shared documents, external data sources, and collaborative activities, and (iii) a recommender system. More specifically, we focus on how knowledge items are extracted from incoming knowledge flows to be proposed to a team, whose members are capable of proposing values for design issues and/or evaluating these choices from her own specific perspective. Furthermore, the aim of the proposed framework is not limited to the selection of relevant knowledge but, more broadly, on aligning the team on a restricted set of information items, producing a convergence of objectives that accelerates the kinetics of the collaborative work.

An anaphora is a type of expression whose reference depends upon another referential element. In order to become aware of situations or human intentions by natural language understanding, it is important to estimate correctly what anaphoric expressions indicate. In particular, an anaphora resolution for Japanese demonstrative determiners is critical to be aware of situation, context or a causal relationship in dialogue. Ontology-based similarity has been proposed as a way to identify referential elements, however, a method using ontology alone cannot resolve all anaphoric relations. This paper proposes an anaphora analysis method that uses semantic similarity between different part-of-speech and conceptual dependency structure. This method specializes in resolving clause anaphoric. The evaluation of this method showed 100% accuracy for resolving Japanese demonstrative determiner in counseling dialogue.

The Service-Oriented Architecture (SOA) paradigm is giving rise to a new generation of applications built by dynamically composing loosely coupled autonomous services. Clients (i.e., software agents acting on behalf of human users or service providers) implementing such complex applications typically search and integrate services on the basis of their functional requirements and of their trust in the service suppliers. A major issue in this scenario relates to the definition of an assurance technique allowing clients to select services on the basis of their nonfunctional requirements and increasing their confidence that the selected services will satisfy such requirements. In this article, we first present an assurance solution that focuses on security and supports a test-based security certification scheme for Web services. The certification scheme is driven by the security properties to be certified and relies upon a formal definition of the service model. The evidence supporting a certified property is computed using a model-based testing approach that, starting from the service model, automatically generates the test cases to be used in the service certification. We also define a set of indexes and metrics that evaluate the assurance level and the quality of the certification process. Finally, we present our evaluation toolkit and experimental results obtained applying our certification solution to a financial service implementing the Interactive Financial eXchange (IFX) standard.

Platform-as-a-Service is a cloud-based approach that provides enterprises with all the functionalities for developing, deploying, and administering services, without the burden of installing, configuring, and managing the underlying middleware, operating system, and hardware. In this context, scalability becomes a fundamental requirement, and appropriate solutions need to be studied and evaluated. In this paper, we present different scalability patterns for a Platform-as-a-Service infrastructure and a two-level approach to performance monitoring allowing automatic scalability management. We also provide a performance evaluation of the scalability patterns on a Service-Oriented Architecture (SOA) PaaS, which considers the impact on performance of SOA security standards.

Bringing sensor- and context-awareness to the Web promises to open new, tremendous business opportunities. However, context-awareness involves difficult problems such as modeling social / human affairs (e.g. law, personal preferences, etc.), handling incomplete information, and managing uncertainty of sensor data. We argue that fully-fledged, Semantic-Web-style reasoning in presence of uncertainty is neither always feasible, nor always necessary for a context-based Web. As an alternative, this paper proposes a highly expressive, simple, and efficient context representation for sensor-enabled Web services. Our representation is based on a syntax inspired by standard Semantics of Business Vocabulary and Business Rules (SBVR), enriched by annotations expressing prioritized modality and trust values. The feasibility of our approach is demonstrated via a case study for developing context/ambient-aware applications that adapt to changes in the environment.

Security certification schemes for Service-Oriented Architecture (SOA) extend service specifications with the evidence that a service supports a set of security properties and provides a given level of assurance. However, services are subject to continuous refinements, and uncontrolled changes can easily invalidate existing certification results and require re-certification from scratch, with high costs and overheads on service providers. In this paper, we present an approach to manage the impact of service evolution on security certification. Our approach aims to support the incremental certification of evolving services and re-use, as much as possible, the certification evidence available from older certificates in the release of a new certificate.

The web services (WS) technology provides a comprehensive solution for representing, discovering, and invoking services in a wide variety of environments, including Service Oriented Architectures (SOA ) and grid computing systems. At the core of WS technology lie a number of XML-based standards, such as the Simple Object Access Protocol (SOAP), that have successfully ensured WS extensibility, transparency, and interoperability. Nonetheless, there is an increasing demand to enhance WS performance, which is severely impaired by XML's verbosity. SOAP communications produce considerable network traffic, making them unfit for distributed, loosely coupled, and heterogeneous computing environments such as the open Internet. Also, they introduce higher latency and processing delays than other technologies, like Java RMI and CORBA. WS research has recently focused on SOAP performance enhancement. Many approaches build on the observation that SOAP message exchange usually involves highly similar messages (those created by the same implementation usually have the same structure, and those sent from a server to multiple clients tend to show similarities in structure and content). Similarity evaluation and differential encoding have thus emerged as SOAP performance enhancement techniques. The main idea is to identify the common parts of SOAP messages, to be processed only once, avoiding a large amount of overhead. Other approaches investigate nontraditional processor architectures, including micro- and macrolevel parallel processing solutions, so as to further increase the processing rates of SOAP/XML software toolkits. This survey paper provides a concise, yet comprehensive review of the research efforts aimed at SOAP performance enhancement. A unified view of the problem is provided, covering almost every phase of SOAP processing, ranging over message parsing, serialization, deserialization, compression, multicasting, security evaluation, and data/instruction-level processing.

SOAP has been widely adopted as a simple, robust and extensible XML-based protocol for the exchange of messages among web services. Unfortunately, SOAP communications have two major performance-related drawbacks: i) verbosity, related to XML, that leads to increased network traffic, and ii) high computational burden of XML parsing and processing, that leads to high latency. In this paper, we address these two issues and introduce a novel framework for Differential SOAP Multicasting (DSM). The main idea consists in identifying the common pattern and differences between SOAP messages, modeled as trees, so as to multicast similar messages together. Our method is based on the well known concept of Tree Edit Distance, built upon a novel filter-differencing architecture to reduce message aggregation time, identifying only those messages which are relevant (i.e., similar enough) for similarity evaluation. In addition, our technique exploits a dedicated differencing output format specifically designed to carry the minimum amount of diff information, in the multicast message, so as to minimize the multicast message size, and therefore reducing the network traffic. The battery of simulation experiments conducted to evaluate our approach shows the relevance of our method in comparison with traditional and dedicated multicasting techniques.

The papers in this special issue focus on research on Service Oriented Architectures (SOA).

Technical enhancements of mobile technologies are paving the way to the definition of high-quality and accurate geolocation solutions based on data collected and managed by GSM/3G networks. We present a technique that provides geolocation and mobility prediction both at network and service level, does not require any change to the existing mobile network infrastructure, and is entirely performed on the mobile network side, making it more robust than other positioning systems with respect to location spoofing and other terminal-based security threats. Our approach is based on a novel database correlation technique over Received Signal Strength Indication (RSSI) data, and provides a geolocation and tracking technique based on advanced map- and mobility-based filtering. The performance of the geolocation algorithm has been carefully validated by an extensive experimentation, carried out on real data collected from the mobile network antennas of a complex urban environment.

The Session Initiation Protocol (SIP) is the de facto standard for multimedia multiparty sessions signalling in Next Generation Networks (NGN). It is the basis of a wide range of IP multimedia services. SIP relies on centralized servers, as per its standard specifications and current usage. However, research has recently begun on the integration of Peer-to-Peer (P2P) principles to SIP to capitalize on the benefits of decentralization. This paper contributes to this research by proposing a novel architecture for P2P SIP. The architecture is an overlay composed of a set of self-organized proxies and distributed registrars. Unlike the architectures proposed to date, it does not extend SIP messages and is P2P middleware independent. This eases implementation, interoperability with legacy, and ensures portability. We have prototyped it using JXTA. JXTA is a P2P middleware that can be deployed on devices ranging from cellular phones to high-end servers and including laptops. Requirements are derived and the related work is discussed. The architecture is presented and the implementation, including the prototype, is described.

This paper describes a methodology and toolkit for the analysis of risks due to insiders' dysfunctional behavior in supply chains. It shows how risk analysis techniques based on value models [15] can incorporate the design and distribution of incentives as a risk-alleviation technique. Some important new functionalities of our SCRS (Supply Chain Risk Simulator v1 [14]) tool are presented. Such functionalities allow for (i) import/export of value models and (ii) execution of incentive-aware risk analysis. Functionality (i) fully integrates the SCRS tool with the e3-value tool suite, increasing synergy with existing value model toolkits. Functionality (ii) substantially extends the original palette of techniques for risk analysis and alleviation. Finally, the paper presents the results of an extensive experimentation of our methodology and simulation tool taking into account different combinations of incentive schemes and simulation options.

In order to improve the reliability and the scalability of content-based retrieval of variant audio tracks from large music databases, we suggest a new multi-stage LSH scheme that consists in (i) extracting compact but accurate representations from audio tracks by exploiting the LSH idea to summarize audio tracks, and (ii) adequately organizing the resulting representations in LSH tables, retaining almost the same accuracy as an exact kNN retrieval. In the first stage, we use major bins of successive chroma features to calculate a multi-probe histogram (MPH) that is concise but retains the information about local temporal correlations. In the second stage, based on the order statistics (OS) of the MPH, we propose a new LSH scheme, OS-LSH, to organize and probe the histograms. The representation and organization of the audio tracks are storage efficient and support robust and scalable retrieval. Extensive experiments over a large dataset with 30,000 real audio tracks confirm the effectiveness and efficiency of the proposed scheme.

This paper addresses the problem of edge restoration in digital images. Taking advantage of an ensemble approach, multiple type-1 fuzzy filters are combined to reach a decision. The fuzzy logic concept for linguistic variables and possibility theory is discussed with regard to knowledge representation and inference procedures. To improve conventional deinterlacing issues, we adopt type-1 fuzzy set concepts to design a weight-measuring approach. We demonstrate that the fuzzy ensemble approach model is well suited to image processing and provide case studies in the video-deinterlacing field. In our proposed method, five fuzzy membership functions (MFs) of linguistic variable-based fuzzy logic filters are derived from the type-1 (a.k.a. ordinary or primary) fuzzy MF. The weight-measuring process of our proposed model is used to assign weights to six candidate deinterlaced pixels (CDPs) that are interpolated according to edge direction. The use of a different MF for each direction allows the filter to characterize each pixel variation influence independently, according to its direction. The weights from all MFs are multiplied with the CDPs. The results of the empirical trials clearly show that the proposed system can successfully deal with several image types containing motion or detail elements.

In today's environment, software companies are engaged in multiple projects delivered on heterogeneous platforms for a wide class of applications in disparate application domains. They are increasingly engaged in the co-development of software systems through joint software development projects including staff from partners and customers as well as their own. As a result, they must support multiple software development processes while trying to guarantee uniform levels of process enactment, and product quality across all projects. Our approach is capable of providing process measurement in a joint-project, multi-process model business environment. It is based on a simple meta-model for computing across-process, multiple-project metrics designed to permit monitoring of CMMI compliance. The open source tool Spago4Q has been developed to support our approach and is capable of producing the measurements needed for monitoring of a set of large-scale development projects using different process models, in a real industrial setting in Europe. The results support the view that that it will not always be possible to aggregate the same set of metrics across disparate process models.

This work presents a flexible XML selection language, FleXPath which allows the formulation of flexible constraints on both structure and content of XML documents. Some experimental results, obtained with a preliminary prototype, are described in order to show that the idea promises good results.

We present a way of building ontologies that proceeds in a bottom-up fashion, defining concepts as clusters of concrete XML objects. Our rough bottom-up ontologies are based on simple relations like association and inheritance, as well as on value restrictions, and can be used to enrich and update existing upper ontologies. Then, we show how automatically generated assertions based on our bottom-up ontologies can be associated with a flexible degree of trust by nonintrusively collecting user feedback in the form of implicit and explicit votes. Dynamic trust-based views on assertions automatically filter out imprecisions and substantially improve metadata quality in the long run

Location-based Access Control (LBAC) techniques allow taking users' physical location into account when determining their access privileges. In this paper, we present an approach to LBAC aimed at integrating location-based conditions along with a generic access control model, so that a requestor can be granted or denied access by checking her location as well as her credentials. Our LBAC model includes a novel way of taking into account the limitations of the technology used to ascertain the location of the requester. Namely, we describe how location verification can be encapsulated as a service, representing location technologies underlying it in terms of two semantically uniform service level agreement (SLA) parameters called confidence and timeout. Based on these parameters, we present the formal definition of a number of location-based predicates, their management, evaluation, and enforcement. The challenges that such an extension to traditional access control policies inevitably carries are discussed also with reference to detailed examples of LBAC policies.

Security is a crucial concern for commercial and mission critical applications in Web-based environments. Semantic Web-style context descriptions aim at supporting widespread distribution of resources and cooperation of autonomous agents on the Web in a secure way. In this paper, context information associated with Access Control (AC) management policies is defined according to basic operators that can be represented using the Web Ontology Language (OWL). The same primitives are used, in the specification of authorizations, to compose domain scope expressions. Standard inference procedures of Description Logics (DL) can then be used to check the consistency of context information referred to by policy conditions and, moreinterestingly, to pre-process context information for grounding policy propagation and enabling conflict resolution. This work aims at extending the notion of modality conflict in the evaluation of AC policies to take into account semantic Web-style, ontology-based definitions of the entities involved.

Abstract Peer‐to‐peer (P2P) applications are rapidly gaining acceptance among users of Internet‐based services, especially because of their capability of exchanging resources while preserving the anonymity of both requesters and providers. However, concerns have been raised about the possibility that malicious users can exploit the network to spread tampered‐with resources (e.g., malicious programs and viruses). A considerable amount of research has thus focused on the development of trust and reputation models in P2P networks. In this article, we propose to use fuzzy techniques in the design of reputation systems based on collecting and aggregating peers' opinions. Fuzzy techniques are used in the evaluation and synthesis of all the opinions expressed by peers. The behavior of the proposed system is described by comparison with probabilistic approaches.

The scope and character of today's computing environments are progressively shifting from traditional, one-on-one client-server interaction to the new cooperative paradigm. It then becomes of primary importance to provide means of protecting the secrecy of the information, while guaranteeing its availability to legitimate clients. Operating online querying services securely on open networks is very difficult; therefore many enterprises outsource their data center operations to external application service providers. A promising direction toward prevention of unauthorized access to outsourced data is represented by encryption. However, data encryption is often supported for the sole purpose of protecting the data in storage while allowing access to plaintext values by the server, which decrypts data for query execution. In this paper, we present a simple yet robust single-server solution for remote querying of encrypted databases on external servers. Our approach is based on the use of indexing information attached to the encrypted database, which can be used by the server to select the data to be returned in response to a query without the need of accessing the plaintext database content. Our indexes balance the trade-off between efficiency requirements in query execution and protection requirements due to possible inference attacks exploiting indexing information. We investigate quantitative measures to model inference exposure and provide some related experimental results.

Spam is one of the major problems of today email systems. While many solutions have been proposed to automatically detect and filter spam, spammers are getting more and more technically sophisticated and aware of internal workings of anti-spam systems, finding ways to disguise their emails to get around the different controls that can be enforced. We propose a decentralized privacy-preserving approach to spam filtering. Our solution exploits robust digests to identify messages that are a slight variation of one another and a structured peer-to-peer architecture between mail servers to collaboratively share knowledge about spam.

We describe the Extreme Programming Ontology (XPO), a formal model specifying the main concepts used in the extreme programming methodology and their properties. XPO's modular structure was developed using the usual normative top down approach to software engineering process modeling. It relies on a set of core components rooted in three main concepts: organisational role, product and phase. Besides being useful for indexing relevant documents and XP artifacts such as user stories and Wiki pages, XPO is aimed at being a sound basis for nonintrusive analysis of agile processes, mining process data about programmers activity and repositories content in order to extract new concepts potentially identifying critical factors in agile software development. Extension to XPO are also discussed, including other agile methodologies and more general software engineering concepts.

The scope and character of today's computing environments are progressively shifting from traditional, one-on-one client-server interaction to the new cooperative paradigm. It then becomes of primary importance to provide means of protecting the secrecy of the information, while guaranteeing its availability to legitimate clients. Operating on-line querying services securely on open networks is very difficult; therefore many enterprises outsource their data center operations to external application service providers. A promising direction towards prevention of unauthorized access to outsourced data is represented by encryption. However, data encryption is often supported for the sole purpose of protecting the data in storage and assumes trust in the server, that decrypts data for query execution.In this paper, we present a simple yet robust single-server solution for remote querying of encrypted databases on untrusted servers. Our approach is based on the use of indexing information attached to the encrypted database which can be used by the server to select the data to be returned in response to a query without the need of disclosing the database content. Our indexes balance the trade off between efficiency requirements in query execution and protection requirements due to possible inference attacks exploiting indexing information. We also investigate quantitative measures to model inference exposure and provide some related experimental results.

Peer-to-peer information sharing environments are increasingly gaining acceptance on the Internet as they provide an infrastructure in which the desired information can be located and downloaded while preserving the anonymity of both requestors and providers. As recent experience with P2P environments such as Gnutella shows, anonymity opens the door to possible misuses and abuses by resource providers exploiting the network as a way to spread tampered-with resources, including malicious programs, such as Trojan Horses and viruses. We propose an approach to P2P security where servants can keep track, and share with others, information about the reputation of their peers. Reputation sharing is based on a distributed polling algorithm by which resource requestors can assess the reliability of perspective providers before initiating the download. The approach complements existing P2P protocols and has a limited impact on current implementations. Furthermore, it keeps the current level of anonymity of requestors and providers, as well as that of the parties sharing their view on others' reputations.

Peer-to-peer (P2P) applications have seen an enormous success, and recently introduced P2P services have reached tens of millions of users. A feature that significantly contributes to the success of many P2P applications is user anonymity. However, anonymity opens the door to possible misuses and abuses, exploiting the P2P network as a way to spread tampered with resources, including Trojan Horses, viruses, and spam. To address this problem we propose a self-regulating system where the P2P network is used to implement a robust reputation mechanism. Reputation sharing is realized through a distributed polling algorithm by which resource requestors can assess the reliability of a resource offered by a participant before initiating the download. This way, spreading of malicious contents will be reduced and eventually blocked. Our approach can be straightforwardly piggybacked on existing P2P protocols and requires modest modifications to current implementations.

Peer-to-peer information sharing environments are increasingly gaining acceptance on the Internet as they provide an infrastructure in which the desired information can be located and downloaded while preserving the anonymity of both requestors and providers. As recent experience with P2P environments such as Gnutella shows, anonymity opens the door to possible misuses and abuses by resource providers exploiting the network as a way to spread tampered with resources, including malicious programs, such as Trojan Horses and viruses.In this paper we propose an approach to P2P security where servents can keep track, and share with others, information about the reputation of their peers. Reputation sharing is based on a distributed polling algorithm by which resource requestors can assess the reliability of perspective providers before initiating the download. The approach nicely complements the existing P2P protocols and has a limited impact on current implementations. Furthermore, it keeps the current level of anonymity of requestors and providers, as well as that of the parties sharing their view on others' reputations.

Web-based applications greatly increase information availability and ease of access, which is optimal for public information. The distribution and sharing of information via the Web that must be accessed in a selective way, such as electronic commerce transactions, require the definition and enforcement of security controls, ensuring that information will be accessible only to authorized entities. Different approaches have been proposed that address the problem of protecting information in a Web system. However, these approaches typically operate at the file-system level, independently of the data that have to be protected from unauthorized accesses. Part of this problem is due to the limitations of HTML, historically used to design Web documents. The extensible markup language (XML), a markup language promoted by the World Wide Web Consortium (W3C), is de facto the standard language for the exchange of information on the Internet and represents an important opportunity to provide fine-grained access control. We present an access control model to protect information distributed on the Web that, by exploiting XML's own capabilities, allows the definition and enforcement of access restrictions directly on the structure and content of the documents. We present a language for the specification of access restrictions, which uses standard notations and concepts, together with a description of a system architecture for access control enforcement based on existing technology. The result is a flexible and powerful security system offering a simple integration with current solutions.

We present an approach for controlling access to data publishers in the framework of Web-based information services. The paper presents a model for enforcing access control regulations, an XML core schema and namespace for expressing such regulations, and illustrates the architecture of the Access Control Unit (ACU), an autonomous software component based on the proposed model. Besides "standard" authorizations, the ACU supports authorizations based on user profiles and dynamic conditions whose outcome is determined by user actions such as the acceptance of a written agreement and/or payment.

Lightweight protocols for remote service invocation via HTTP and XML, such as SOAP, are rapidly gaining acceptance among developers of Internet-based e-services, especially because of their rewall-traversal capabilities. However, no standard technique for access control security is currently defined for either HTTP or SOAP itself. Concerns have been raised about the possibility that different SOAP applications will deal with embedded security in different ways, leading to application-dependent security holes. In this paper, we propose an approach that relies on the XML structure of SOAP requests to support fine-grained authorizations at the level of individual XML elements and attributes that compose a SOAP call. The result is a simple, yet powerful and general, technique to enforce access restrictions to SOAP invocations.

In network-centered execution environments, client objects can transparently invoke services offered by remote server objects, according to their published interface. The object selection problem requires the evaluation of the fitness of a pool of candidate server objects on the basis of the available information about their functional and nonfunctional features. Network-centered systems usually store such information in a trader agent that can be browsed or queried by client objects. In this paper, a fuzzy data model is proposed as the basis of the design of such a trader system, taking into account synergy between objects' features. Our trader is based on a fuzzy query algebra allowing for deriving operator definitions (therefore, query execution mechanisms) at run time, on the basis of user-selected semantics.

The rapid evolution of XML from a mere data exchange format to a universal syntax for encoding domain-specific information raises the need for new query languages specifically conceived to address the characteristics of XML. Such languages should be able not only to extract information from XML documents, but also to apply powerful transformation and restructuring operators, based on a well-defined semantics. Moreover, XML queries should be natural to write and understand, as nontechnical persons also are expected to access the large XML information bases supporting their businesses. This article describes XML-GL, a graphical query language for XML data. XML-GL's uniqueness is in the definition of a graph-based syntax to express a wide variety of XML queries, ranging from simple selections to expressive data transformations involving grouping, aggregation, and arithmetic calculations. XML-GL has an operational semantics based on the notion of graph matching, which serves as a guideline both for the implementation of native processors, and for the adoption of XML-GL as a front-end to any of the XML query languages that are presently under discussion as the standard paradigm for querying XML data.

In this paper we deal with the problem of querying, navigating and exchanging UML design artefacts, including components interfaces, conceptual schemas and the like. Our approach relies on a hierarchy of XML-based descriptors for UML components, representing both functional and non-functional features of artefacts. After presenting a “query-friendly” DTD for such descriptors, the paper illustrates issues related to querying and browsing design repositories. We show how our approach can also address connection-oriented services, such as HTTP-based Web sites.

The object selection problem requires the evaluation of the fitness of a candidate server object to execute a certain task on the basis of the information about its functional and non-functional features. Active networks store such information in a Trader agent that can be browsed or queried by client objects. In this paper, a fuzzy data model is proposed as the basis of the design of a Trader system. Such a Trader is based on a fuzzy query algebra allowing for deriving operator definitions (and, therefore, query execution mechanisms) at run time, on the basis of user-selected semantics.

An increasing number of XML (eXtensible Markup Language) documents available on the World Wide Web have no document type definition (DTD); still, most current query languages for XML rely on the user knowing the DTD when composing queries on XML data. In this paper, a flexible query model for well-formed XML documents without DTDs is outlined.

This article presents a hierarchy-aware classification schema for obje ct-oriented code, where software components are classified according to their behavioral characteristics , such as provided services, employed algorithms, and needed data. In the case of reusable application frameworks, these characteristics are constructured from their model , i.e., from the description of the abstract classes specifying both the framework structure and purpose. In conventional object libraries, the characteristics are extracted semiautomatically from class interfaces. Characteristics are term pairs, weighted to represent “how well” they describe component behavior. The set of characteristics associated with a given component forms its software descriptor . A descriptor base is presented where descriptors are organized on the basis of structured relationships, such as similarity and composition. The classification is supported by a thesaurus acting as a language-independent unified lexicon. The descriptor base is conceived for developers who, besides conventionally browsing the descriptors hierarchy, can query the system, specifying a set of desired functionalities and getting a ranked set of adaptable candidates. User feedback is taken into account in order to progressively ameliorate the quality of the descriptors according to the views of the user community. Feedback is made dependent of the user typology through a user profile . Experimental results in terms of recall and precision of the retrieval mechanism against a sample code base are reported.

This article presents a hierarchy-aware classification schema for object-oriented code, where software components are classified according to their behavioral characteristics , such as provided services, employed algorithms, and needed data. In the case of reusable application frameworks, these characteristics are constructed from their model , i.e., from the description of the abstract classes specifying both the framework structure and purpose. In conventional object libraries, the characteristics are extracted semiautomatically from class interfaces. Characteristics are term pairs, weighted to represent "how well" they describe component behavior. The set of characteristics associated with a given component forms its software descriptor . A descriptor base is presented where descriptors are organized on the basis of structured relationships, such as similarity and composition. The classification is supported by a thesaurus acting as a language-independent unified lexicon. The descriptor base is conceived for developers who, besides conventionally browsing the descriptors hierarchy, can query the system, specifying a set of desired functionalities and getting a ranked set of adaptable candidates. User feedback is taken into account in order to progressively ameliorate the quality of the descriptors according to the views of the user community. Feedback is made dependent of the user typology through a user profile . Experimental results in terms of recall and precision of the retrieval mechanism against a sample code base are reported.

During application development under reuse, much effort is spent in retrieving suitable components. This paper presents an approach to retrieval based on software descriptions of components, and on a mechanism for computing the functional similarity of clusters of reuse candidates. Descriptions are given in a semi-formal fashion and using fuzzy weights for keywords. Algorithms for similarity computation are presented. The experimental tool for this approach manages imprecise queries posed by developers against a software repository; results about reuse of object-oriented code based on the use of the tool are presented, giving measures of recall and precision of the proposed approach.