Effective agent coordination is crucial in cooperative Multiagent Reinforcement Learning (MARL). While recent advances have significantly improved cooperation by modeling agent interactions through various graph structures, most existing approaches primarily focus on homogeneous agents. Despite the ubiquity of heterogeneous agents, constructing a comprehensive graph that captures their diverse attributes and relationships from scratch is notoriously labor-intensive for both humans and agents, which makes policy learning extremely challenging. To tackle this difficulty, we propose a novel method that utilizes a fuzzy human attention-guided graph to model inter-agent relationships. Instead of learning the graph entirely from scratch, we incorporate abstract human attention, with its uncertainty captured through fuzzy logic, to guide the graph development process. To further accommodate the varying attributes and objectives of heterogeneous agents while maintaining their learning capabilities, the attention-guided graph is fine-tuned through a hyper-network. Our proposed approach is end-to-end trainable and agnostic to specific MARL methods. Empirical evaluations conducted on challenging heterogeneous scenarios from the StarCraft Multiagent Challenge (SMAC) and SMACv2 validate the effectiveness of the proposed method.

As one of the primary causes of visual impairment, Diabetic Retinopathy (DR) requires accurate and robust grading to facilitate timely diagnosis and intervention. Different from conventional DR grading methods that utilize single-view images, recent clinical studies have revealed that multi-view fundus images can significantly enhance DR grading performance by expanding the field of view (FOV). However, there is a long-tailed distribution problem in fundus image analysis, i.e., a high prevalence of mild DR grades and a low prevalence of rare ones (e.g., cases of high severity), which presents a significant challenge to developing a unified model capable of detecting rare or unseen DR grades not encountered during training. In this paper, we propose ProME-DR, a Prompt-driven zero-shot DR grading framework, which leverages prompt Matching and Emulating to recognize the unseen DR categories and views beyond the training set. ProME-DR disentangles the training process into two stages to learn generalized knowledge for novel DR disease grading. Initially, ProME-DR leverages two sets of prompt units to capture semantic and inter-view consistency knowledge via a split-and-mask manner, gathering instance-level DR visual clues. Subsequently, it constructs a concept-aware emulator to generate context prompt units, linking extensible knowledge learned from the previously seen DR attributes for zero-shot DR grading. Extensive experiments conducted on eight datasets and various scenarios confirm the superiority of ProME-DR.

Abstract Due to its exceptional learning ability, multi-agent deep reinforcement learning (MADRL) has garnered widespread research interest. However, since the learning is data-driven and involves sampling from millions of steps, training a large number of agents is inherently challenging and inefficient. Inspired by the human learning process, we aim to transfer knowledge from humans to avoid starting from scratch. Given the growing emphasis on the Human-on-the-Loop concept, this study focuses on addressing the challenges of large-population learning by incorporating suboptimal human knowledge into the cooperative multi-agent environment. To leverage human experience, we integrate human knowledge into the training process of MADRL, representing it in natural language rather than specific action-state pairs. Compared to previous works, we further consider the attributes of transferred knowledge to assess its impact on algorithm scalability. Additionally, we examine several features of knowledge mapping to effectively convert human knowledge to the action space where agent learning occurs. In reaction to the disparity in knowledge construction between humans and agents, our approach allows agents to decide freely which portions of the state space to leverage human knowledge. From the challenging domains of the StarCraft Multi-agent Challenge, our method successfully alleviates the scalability issue in MADRL. Furthermore, we find that, despite individual-type knowledge significantly accelerating the training process, cooperative-type knowledge is more desirable for addressing a large agent population. We hope this study provides valuable insights into applying and mapping human knowledge, ultimately enhancing the interpretability of agent behavior.

Following the digital wave, KEEP has become a popular fitness app in China due to its unique gamification design. Research suggests that the influences of the app may be key to changing users’ motivations for using fitness apps. In this study, we focused on identifying which factors were more salient to users in the short and long term and explored whether gamification had a negative impact. Taking KEEP as an example, we used semi-structured interviews and participant observations to collect data and employed thematic analysis to facilitate in-depth interpretation. We found that (1) health awareness and the pursuit of fitness are the initial motivations for users to use gamified fitness apps, while fun and a sense of achievement can increase users’ exercise persistence in the short term; (2) in the long term, reward motivation, stress, and habits play important roles in users’ persistent use behaviour, while a sense of achievement provides positive incentives for long-term use; (3) excessive gamification may cause users to feel excessive stress and even trigger emotional exhaustion. These findings not only provide new perspectives to help fitness app operators optimise the user experience, but also alert them to the potential risks of gamification.

While ridesharing provides substantial convenience, it also raises several security concerns, with location privacy being a primary issue. A common state-of-the-art solution is to add random noise to user locations to preserve privacy. However, this approach often degrades matching efficiency due to reduced location accuracy. In this paper, we study the real-time matching problem between ridesharing requests and drivers, aiming to maintain high matching efficiency despite obfuscated locations. We model the order dispatching process as an online bipartite matching problem, where drivers are offline and requests arrive sequentially following a known distribution. We construct benchmark linear programs (LPs) and propose an LP-based online matching algorithm with provable performance guarantees. To address privacy concerns, we further develop a privacy-aware LP-based method that mitigates the impact of Laplace noise. Experiments on real-world datasets demonstrate the effectiveness of our algorithms and support our theoretical findings.

Prompt learning has emerged as an efficient tuning paradigm for fine-tuning powerful pre-trained models on downstream tasks in specific domains. Existing efforts mainly focus on dataset-level implicit embeddings by introducing extra learnable parameters instead of fully fine-tuning large-scale visual models. However, we find that these static post-training prompts are not flexible enough to adapt various input instances within the same dataset, which might lead to the loss of the model's generalization capability. To leverage the meaningful contextual information of each input instance, in this paper, we propose a straightforward yet effective method, termed CoMoDP, to enhance visual prompt learning withContext-ModulatedDiffusionPrompts. Specifically, CoMoDP is a dual-visual prompting scheme that comprises two key components:(i) a unified visual prompt designer, producing dataset-level implicit embedding as unified prompts for efficient adaptation without corrupting the underlying information of the original image; and(ii) a diffusion prompt simulator, leveraging diffusion model's meticulous understanding of semantic structure and texture edges in the images to dynamically generate instance-level implicit embedding as diffusion prompts for input samples. Moreover, to reduce the overfitting of prompts, we also introduce momentum alignment, a self-regulating strategy that restricts the optimization region of prompts in both feature and logit spaces. Extensive experiments on various standard and few-shot datasets demonstrate that our method brings substantial improvements and yields strong domain generalization performance, compared to the state-of-the-art methods. We also demonstrate both zero-shot and out-of-distribution performance to establish the utility of our dual-visual prompting scheme CoMoDP and the efficiency of each component, without involving excessive parameters.

Federated learning aims at training models collaboratively across participants while protecting privacy. However, one major challenge for this paradigm is the data heterogeneity issue, where biased data preferences across multiple clients, harming the model's convergence and performance. In this paper, we first introduce powerful diffusion models into the federated learning paradigm and show that diffusion representations are effective steers during federated training. To explore the possibility of using diffusion representations in handling data heterogeneity, we propose a novel diffusion-inspired Federated paradigm with Diffusion Representation Collaboration, termed FedDifRC, leveraging meaningful guidance of diffusion models to mitigate data heterogeneity. The key idea is to construct text-driven diffusion contrasting and noise-driven diffusion regularization, aiming to provide abundant class-related semantic information and consistent convergence signals. On the one hand, we exploit the conditional feedback from the diffusion model for different text prompts to build a text-driven contrastive learning strategy. On the other hand, we introduce a noise-driven consistency regularization to align local instances with diffusion denoising representations, constraining the optimization region in the feature space. In addition, FedDifRC can be extended to a self-supervised scheme without relying on any labeled data. We also provide a theoretical analysis for FedDifRC to ensure convergence under non-convex objectives. The experiments on different scenarios validate the effectiveness of FedDifRC and the efficiency of crucial components.

With the advancement of edge computing, federated learning (FL) displays a bright promise as a privacy-preserving collaborative learning paradigm. However, one major challenge for FL is the data heterogeneity issue, which refers to the biased labeling preferences among multiple clients, negatively impacting convergence and model performance. Most previous FL methods attempt to tackle the data heterogeneity issue locally or globally, neglecting underlying class-wise structure information contained in each client. In this paper, we first study how data heterogeneity affects the divergence of the model and decompose it into local, global, and sampling drift sub-problems. To explore the potential of using intra-client class-wise structural knowledge in handling these drifts, we thus propose Federated Learning with Structural Knowledge Collaboration (FedSKC). The key idea of FedSKC is to extract and transfer domain preferences from inter-client data distributions, offering diverse class-relevant knowledge and a fair convergent signal. FedSKC comprises three components: i) local contrastive learning, to prevent weight divergence resulting from local training; ii) global discrepancy aggregation, which addresses the parameter deviation between the server and clients; iii) global period review, correcting for the sampling drift introduced by the server randomly selecting devices. We have theoretically analyzed FedSKC under non-convex objectives and empirically validated its superiority through extensive experimental results. Our code is at https://github.com/hwang52/FedSKC.

Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving.However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at multiple clients.A number of existing FL methods attempt to tackle data heterogeneity locally (e.g., regularizing local models) or globally (e.g., fine-tuning global model), often neglecting inherent semantic information contained in each client.To explore the possibility of using intra-client semantically meaningful knowledge in handling data heterogeneity, in this paper, we propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients.The core idea of FedSC is to construct relational prototypes and consistent prototypes at semantic-level, aiming to provide fruitful class underlying knowledge and stable convergence signals in a prototype-wise collaborative way.On the one hand, FedSC introduces an inter-contrastive learning strategy to bring instance-level embeddings closer to relational prototypes with the same semantics and away from distinct classes.On the other hand, FedSC devises consistent prototypes via a discrepancy aggregation manner, as a regularization penalty to constrain the optimization region of the local model.Moreover, a theoretical analysis for FedSC is provided to ensure a convergence guarantee.Experimental results on various challenging scenarios demonstrate the effectiveness of FedSC and the efficiency of crucial components.Our code is at https://github.com/hwang52/FedSC.

A significant threat to GPS users, including Unmanned Aerial Vehicles (UAVs), is the location spoofing attack, which can mislead systems with false GPS signals, jeopardising their operations and safety. To address this challenge, this study presents a method for verifying GPS spoofing attacks on UAV systems. The proposed solution develops a robust methodology by analysing the reported position of the UAV, along with various features of the received signal, such as the signal-to-noise ratio (SNR), azimuth, and pitch angles, at multiple base stations. Additionally, we consider Nakagami fading channels to model the properties of the received signal, which are relevant to real-world scenarios. We developed a smart verification algorithm using the Recurrent Neural Network (RNN) to authenticate the position reported by UAVs based on SNR, azimuth, and pitch angle data at various base station antennas. We have utilised both simple recurrent neural network (SRNN) and long short-term memory (LSTM) algorithms to evaluate and compare the performance of the model by varying the number of base stations. The performance of the algorithm was evaluated using confusion metrics, including accuracy, precision, and the F1 score. In addition, we have compared the performance of the proposed model with the models proposed in the previous study, which were built based on the received signal strength (RSS). The results show that the effectiveness of the models improves as the number of base stations increases.

Deep neural network (DNN)-based vehicle detection systems deployed on unmanned aerial vehicles (UAVs) are susceptible to adversarial attacks, resulting in significant implications for public safety and system reliability. Despite advancements in DNN-based detection, the adversarial robustness of these systems in aerial video contexts remains underexplored. Existing attack models fail to exploit the sequential and periodic nature of video frames in aerial vehicle detection systems. To address this, we propose a Periodic Adversarial Attack for Aerial Video (P3AV), which is the first to take advantage of the periodic nature of tasks related to road traffic parameters and improve the success of attacks. P3AV systematically selects critical video frames to be attacked by employing Bayesian optimization combined with domain-specific knowledge. The sensitive pixels in the frames are then chosen based on the gradient magnitudes of the loss function. Finally, an improved version of the projected gradient descent algorithm is developed by using gradient norms to generate perturbations and enhance the manipulation of selected pixels. Our experiments using four adversarial attacks against 10 DNN architectures, which are developed based on Convolutional Neural Network (CNN) and YOLO, on two datasets demonstrate that P3AV can improve the false rate in detection systems by 6% and the attack success rate by 5% over other attack models. Meanwhile, CNN models perform the worst against adversarial attacks. These findings highlight the critical need for improved adversarial defenses in UAV-based detection systems and underscore the broader implications for secure and reliable ITS.

Due to the exponential growth of agent interactions and the curse of dimensionality, learning efficient coordination from scratch is inherently challenging in large-scale multi-agent systems. While agents' learning is data-driven, sampling from millions of steps, human learning processes are quite different. Inspired by the concept of Human-on-the-Loop and the daily human hierarchical control, we propose a novel knowledge-guided multi-agent reinforcement learning framework (hhk-MARL), which combines human abstract knowledge with hierarchical reinforcement learning to address the learning difficulties among a large number of agents. In this work, fuzzy logic is applied to represent human suboptimal knowledge, and agents are allowed to freely decide how to leverage the proposed prior knowledge. Additionally, a graph-based group controller is built to enhance agent coordination. The proposed framework is end-to-end and compatible with various existing algorithms. We conduct experiments in challenging domains of the StarCraft Multi-agent Challenge combined with three famous algorithms: IQL, QMIX, and Qatten. The results show that our approach can greatly accelerate the training process and improve the final performance, even based on low-performance human prior knowledge.

Unmanned Aerial Vehicles (UAVs), or drones, are increasingly used in various fields. A major concern with UAV operation is their limited power capacity which impacts mission planning, operational efficiency, and battery management, presenting significant research and engineering challenges. This paper evaluates the applications of multiple AI algorithms in predicting the energy consumption of low-cost quadcopter drones. One of the primary contributions involves developing four prediction models, including random forest, regression tree, support vector machine, artificial neural network, and adaptive Neuro-Fuzzy Inference System (ANFIS) on an open-source dataset of small quadcopter flights. This paper also performs a comparative study on the performance of the aforementioned algorithms in predicting the energy consumption of a UAV. This research enhances the field not only by leveraging established machine learning techniques but also by adopting and examining ANFIS, which has received limited prior research attention. By introducing and applying ANFIS, this study not only expands the existing knowledge but also offers a unique perspective, potentially paving the way for further research, especially in addressing uncertainty like weather conditions. According to our study, the power consumption of the UAV is notably influenced by the aircraft’s altitude, wind speed, and velocity. The Random Forest model demonstrates superior accuracy in forecasting UAV power consumption compared to other models. We also provide an overview of the ongoing challenges and potential future endeavors.

The increased reliance on Unmanned Aerial Vehicles (UAVs) in various industries exalts the security requirements since it is critical to protect these systems from any cyber-attack. GPS spoofing presents an important challenge by deceiving UAVs through false GPS signals that would disrupt their operations, thereby endangering them. As a countermeasure, this study introduces a method of detecting GPS spoofing attacks that are aimed at UAV systems. This involves developing a robust methodology to detect the GPS spoofing attack based on the UAV’s current reported location and Received Signal Strength (RSS) data at several base stations. In this study, we developed a smart verification algorithm using the K-Nearest Neighbors (KNN) algorithm to authenticate the reported locations of UAVs, based on RSS from various base stations antenna. We evaluated the performance of the algorithm using metrics such as accuracy, precision, and F1-score. The results indicate that the algorithm’s effectiveness improves with an increase in the number of base stations used. Additionally, the paper will pinpoint the possible direction for UAV security and the adaptive countermeasures to improve the level of resilience against spoofing tactics, which are rapidly evolving.

Data consistency is a challenge for designing energy-efficient medium access control protocols used in IoT. The energy-efficient data consistency method makes the protocol suitable for low, medium, and high data rate applications. In this work, the idea of an energy-efficient data consistency protocol is proposed with data aggregation. The proposed protocol efficiently utilizes the data rate as well as saves energy with guaranteed consistency. The idea of an optimal sampling rate selection method is introduced for maintaining the data consistency of continuous and periodic monitoring nodes in an energy-efficient manner. In the starting phase, the nodes will be classified into the event and continuous monitoring nodes. The machine learning-based logistic classification method is used for the classification of nodes. The sampling rate of continuous monitoring nodes is optimized during the setup phase by using the Optimized sampling rate data aggregation algorithm. Furthermore, an energy-efficient time division multiple access (EETDMA) protocol is used for the continuous monitoring of IoT devices, and an energy-efficient bit map assisted (EEBMA) protocol is proposed for the event-driven nodes. The simulation results prove the superiority of the proposed protocol with respect to existing work.

In recent years, especially during COVID, an increasing number of adult learners are flocking to e-learning platforms or mobile Apps for either personal or professional development. This research is built upon the constructivism model to investigate adult learners’ satisfaction, perceived learning outcome, and recommendations towards Educational Key Opinion Leaders (Edu-KOLs). A two-phase study was designed specifically for this purpose, firstly using an online questionnaire distributed via the WeChat Platform to 203 per-qualified adult learners in China, followed by a one-on-one interview with selected ten. We adopted the quantitative research approach using partial least squares structural equation modelling (PLS-SEM) to interpret the collected data. The findings revealed that Edu-KOLs’ knowledge level and course content have a significant influence on learners’ perceived learning outcomes and customer advocacy. It was also indicated that higher engagement and interaction levels are favourably associated with their advocacy for the course and review for future potential learners.

In recent years, an increasing number of school-age children and adult learners are flocking to e-learning platforms or mobile Apps for personal or professional development. This research compared two studies that were built upon the constructivism model to investigate the parents, whose children are studying or have recently studied online, and also the adult learners' satisfaction, perceived learning outcomes, and recommendations towards Educational Key Opinion Leaders (Edu-KOLs). A two-phase study was designed specifically for both studies. We adopted the quantitative research approach using partial least squares structural equation modelling (PLS-SEM) to interpret the collected data. The findings revealed that for both learning cohorts, Edu-KOLs' knowledge level and course content has a significant influence on learners' perceived learning outcomes and customer advocacy and that higher engagement and interaction levels are favourably associated with their perception of Edu-KOLs. However, the e-learning platform played a positive role in selecting Edu-KOLs for parents but was not significant for adult learners. Perceived outcomes are critical for adult learners, whereas parents are satisfied as long as children are engaged, regardless of what they have learned.

In this study, the trusted third party (TTP) in Australia's B2C marketplace is studied and the factors influencing consumers' trust behaviour are examined from the perspective of consumers' online trust. Based on the literature review and combined with the development status and background of Australia's e-commerce, underpinned by the Theory of Planned Behaviour (TPB) and a conceptual trust model, this paper expatiates the specific factors and influence mechanism of TTP on consumers' trust behaviour. Also this paper explains two different functions of TTP to solve the online trust problem faced by consumers. Meanwhile, this paper summarizes five different types of services provided by TTPs during the establishment of the trust relationship. Finally, the present study selects 100 B2C enterprises by the simple random sampling method and makes a detailed analysis of their TTPs, to verify the services and functions of the proposed TTP in the trust model. This study is of some significance for comprehending the influence mechanism, functions and services of TTPs on consumers' trust behaviour in the realistic Australian B2C environment.

Data transfer is a transmission of data over a point-to-point or point-to-multipoint communication channel. To protect the confidentiality of the transferred data, public-key cryptography has been introduced in data transfer schemes (DTSs). Data transfer is a transmission of data over a point-to-point or point-to-multipoint communication channel. To protect the confidentiality of the transferred data, public-key cryptography has been introduced in data transfer schemes (DTSs). Unfortunately, there exist some drawbacks in the current DTSs. First, the sender must know who the real receivers are. This is undesirable in a system where the number of the users is very large, such as cloud computing. In practice, the sender only knows some descriptive attributes of the receivers. Secondly, the receiver cannot be guaranteed to only receive messages from the legal senders. Therefore, it remains an elusive and challenging research problem on how to design a DTS scheme where the sender can send messages to the unknown receivers and the receiver can filter out false messages according to the described attributes. In this paper, we propose an attribute-based data transfer with filtering (ABDTF) scheme to address these problems. In our proposed scheme, the receiver can publish an access structure so that only the users whose attributes satisfy this access structure can send messages to him. Furthermore, the sender can encrypt a message under a set of attributes such that only the users who hold these attributes can obtain the message. In particular, we provide an efficient filtering algorithm for the receiver to resist the denial-of-service attacks. Notably, we propose the formal definition and security models for ABDTF schemes. To the best of our knowledge, it is the first time that a provable ABDTF scheme is proposed. Hence, this work provides a new research approach to ABDTF schemes. must know who are the real receivers. This is undesirable in a system where the number of the users is very large, such as cloud computing. In practice, the sender only knows some descriptive attributes of the receivers. Second, the receiver cannot be guaranteed to only receive messages from the legal senders. Therefore, it remains an elusive and challenging research problem on how to design a DTS scheme where the sender can send messages to the unknown receivers and the receiver can filter out false messages according to the described attributes. In this paper, we propose an attribute-based data transfer with filtering (ABDTF) scheme to address these problems. In our proposed scheme, the receiver can publish an access structure so that only the users whose attributes satisfy this access structure can send messages to him. Furthermore, the sender can encrypt a message under a set of attributes such that only the users who hold these attributes can obtain the message. In particular, we provide an efficient filtering algorithm for the receiver to resist the denial-of-service (DoS) attacks. Notably, we propose the formal definition and security models for ABDTF schemes. To the best of our knowledge, it is the first time that a provable ABDTF scheme is proposed. Hence, this work provides a new research approach to ABDTF schemes.

SUMMARY Service selection in service‐oriented computing has emerged to be an increasingly important research area. From the client's point of view, in addition to the QoS of a service or a service composition, the trust level becomes an important part. As the complexity of invocation in service composition has been greatly increased, a comprehensive mechanism, which could evaluate both the subjective aspect as trust expression and the objective aspect as QoS, is needed. In this paper, we provide a formal service composition architecture for service selection. In addition, we propose a trust evaluation method for the service composition plan based on the subjective probability theory, based on them, our trust‐oriented genetic algorithm (TOGA) is proposed to find a near‐optimal service composition plan with QoS constraints. Experimental results have illustrated that our proposed approach can discover the near‐optimal solution efficiently. Copyright © 2013 John Wiley & Sons, Ltd.

The service-oriented paradigm offers support for engineering service-based systems (SBSs) based on service composition where existing services are composed to create new services. The selection of services with the aim to fulfil the quality constraints becomes critical and challenging to the success of SBSs, especially when the quality constraints are stringent. However, none of the existing approaches for quality-aware service composition has sufficiently considered the following two critical issues to increase the success rate of finding a solution: 1) the complementarities between services; and 2) the competition among service providers. This paper proposes a novel approach called combinatorial auction for service selection (CASS) to support effective and efficient service selection for SBSs based on combinatorial auction. In CASS, service providers can bid for combinations of services and apply discounts or premiums to their offers for the multi-dimensional quality of the services. Based on received bids, CASS attempts to find a solution that achieves the SBS owner's optimisation goal while fulfilling all quality constraints for the SBS. When a solution cannot be found based on current bids, the auction iterates so that service providers can improve their bids to increase their chances of winning. This paper systematically describes the auction process and the supporting mechanisms. Experimental results show that by exploiting the complementarities between services and the competition among service providers, CASS significantly outperforms existing quality-aware service selection approaches in finding optimal solutions and guaranteeing system optimality. Meanwhile, the duration and coordination overhead of CASS are kept at satisfactory levels in scenarios on different scales.

Service-Oriented Computing (SOC) is emerging as a paradigm for developing distributed applications. A critical issue of utilizing SOC is to have a scalable, reliable, and robust service discovery mechanism. However, traditional service discovery methods using centralized registries can easily suffer from problems such as performance bottleneck and vulnerability to failures in large scalable service networks, thus functioning abnormally. To address these problems, this paper proposes a peer-to-peer-based decentralized service discovery approach named Chord4S. Chord4S utilizes the data distribution and lookup capabilities of the popular Chord to distribute and discover services in a decentralized manner. Data availability is further improved by distributing published descriptions of functionally equivalent services to different successor nodes that are organized into virtual segments in the Chord4S circle. Based on the service publication approach, Chord4S supports QoS-aware service discovery. Chord4S also supports service discovery with wildcard(s). In addition, the Chord routing protocol is extended to support efficient discovery of multiple services with a single query. This enables late negotiation of Service Level Agreements (SLAs) between service consumers and multiple candidate service providers. The experimental evaluation shows that Chord4S achieves higher data availability and provides efficient query with reasonable overhead.

In an attribute-based system (ABS), users are identified by various attributes, instead of their identities. Since its seminal introduction, the attribute-based mechanism has attracted a lot of attention. However, current ABS schemes have a number of drawbacks: (i) the communication cost is linear in the number of the required attributes; (ii) the computation cost is linear in the number of the required attributes and (iii) there are no efficient verification algorithms for the secret keys. These drawbacks limit the use of ABS in practice. In this paper, we propose an attribute-based oblivious access control (ABOAC) scheme to address these problems, where only the receiver whose attributes satisfy the access policies can obtain services obliviously. As a result, the receiver does not release anything about the contents of the selected services and his attributes to the sender, and even the number and supersets of his attributes are protected. The sender only knows the number of the services selected by the authorized receiver. Notably, the costs of computation and communication are constant and independent of the number of required attributes. While, in the prior comparable schemes, both the costs of computation and communication are linear in the required attributes. Therefore, our ABOAC scheme provides a novel and elegant solution to protect user's privacy in the systems where both the bandwidth and the computing capability are limited, such as wireless sensor and actor networks, mobile ad hoc networks, etc..

SUMMARY Cloud computing has increasingly become a new model in the world of computing, and more businesses are moving to the cloud. As a cost‐effective and time‐efficient way to develop new applications and services, service aggregation in cloud computing empowers all service providers and consumers and creates tremendous opportunities in various industry sectors. However, it also poses various challenges to the privacy of personal information as well as the confidentiality of business and governmental information. The full benefits of service aggregation in cloud computing would only be enjoyed if the privacy concerns are addressed properly. In this paper, we investigate the privacy issues in service aggregation in a cloudenvironment and propose a privacy preserving protocol that is suitable for this environment. To demonstrate the security of our system, we construct a security game called IND‐P3SAC‐CPA and prove the security of the protocol accordingly. Our protocol has a distinct property that allows any service provider to obtain only the queried data under its conspiracy with the cloud. Additionally, the efficiency and various extensions are also discussed. Copyright © 2011 John Wiley & Sons, Ltd.

Decentralized attribute-based encryption (ABE) is a variant of a multiauthority ABE scheme where each authority can issue secret keys to the user independently without any cooperation and a central authority. This is in contrast to the previous constructions, where multiple authorities must be online and setup the system interactively, which is impractical. Hence, it is clear that a decentralized ABE scheme eliminates the heavy communication cost and the need for collaborative computation in the setup stage. Furthermore, every authority can join or leave the system freely without the necessity of reinitializing the system. In contemporary multiauthority ABE schemes, a user's secret keys from different authorities must be tied to his global identifier (GID) to resist the collusion attack. However, this will compromise the user's privacy. Multiple authorities can collaborate to trace the user by his GID, collect his attributes, then impersonate him. Therefore, constructing a decentralized ABE scheme with privacy-preserving remains a challenging research problem. In this paper, we propose a privacy-preserving decentralized key-policy ABE scheme where each authority can issue secret keys to a user independently without knowing anything about his GID. Therefore, even if multiple authorities are corrupted, they cannot collect the user's attributes by tracing his GID. Notably, our scheme only requires standard complexity assumptions (e.g., decisional bilinear Diffie-Hellman) and does not require any cooperation between the multiple authorities, in contrast to the previous comparable scheme that requires nonstandard complexity assumptions (e.g., q-decisional Diffie-Hellman inversion) and interactions among multiple authorities. To the best of our knowledge, it is the first decentralized ABE scheme with privacy-preserving based on standard complexity assumptions.

Personalisation is becoming more important in the area of mobile learning. Learner model is logically partitioned into smaller elements or classes in the form of learner profiles, which can represent the entire learning process. Machine learning techniques have the ability to detect patterns from complicated data and learn how to perform activities based on learner profiles. This paper focuses on a systematic approach in reasoning the learner contexts to deliver adaptive learning content. A fuzzy rule base model that has been proposed in related work is found insufficient in deciding all possible conditions. To tackle this problem, this paper adopts the Adaptive Neuro-Fuzzy Inference System (ANFIS) approach to determine all possible conditions. ANFIS uses the hybrid (least-squares method and the back propagation gradient descent method) as learning mechanism for the Neural Network to determine the incompleteness in the decision made by human experts. The simulating results by Matlab indicate that the performance of ANFIS approach is valuable and easy to implement.

The problem of access control on outsourced data to "honest but curious" cloud servers has received considerable attention, especially in scenarios involving potentially huge sets of data files, where re-encryption and re-transmission by the data owner may not be acceptable. Considering the user privacy and data security in cloud environment, in this paper, we propose a solution to achieve flexible and fine-grained access control on outsourced data files. In particular, we look at the problem of defining and assigning keys to users based on different attribute sets, and hiding access policies as well as users information to the third-party cloud servers. Our proposed scheme is partially based on our observation that, in practical application scenarios each user can be associated with a set of attributes which are meaningful in the access policy and data file context. The access policy can thus be defined as a logical expression formula over different attribute sets to reflect the scope of data file that the kind of users is allowed to access. As any access policy can be represented as such a logical expression formula, fine-grained access control can be accomplished.

With a rapid growth of the Internet, exploring cost-effective and time-efficient methods for creating Internet services has become critical. As an emerging technology, service aggregation has been regarded as a promising candidate. However, it also raises serious issues on privacy management, as a service is usually provided by multiple providers that are usually transparent to its users. We observe that these issues have not been formally studied in the literature. In this paper, we propose a formal model for the privacy management in service aggregation and present a negotiation strategy on different privacy policies between two organizations.

Personalisation and learner modelling are becoming more important in the area of mobile learning applications, taking into consideration learners' interests, preferences and contextual information. Students nowadays are able to learn anywhere and at any time. Mobile learning application content is one of several factors within various contexts that play an important role in the success of the adaptation process. The vast amount of data involved in any successful adaptation process creates complexity and poses serious challenges. This paper focuses on how to model the learner and all possible contexts in an extensible way that can be used for personalisation in mobile learning. The enhanced learner modelling structure to be used in a mobile learning system is proposed. The proposed structure provides personalisation by adopting a hybrid approach combining two machine learning techniques.

The goal of federated identity management is to allow principals, such as identities and attributes, to be shared across trust boundaries based on established policies. Since current Single Sign-On (SSO) mechanism excessively relies on the specifications of Circle of Trust (CoT), the need for service collaboration from different domains is being addressed on CoT. For the motivating issue of the cross-domain SSO mechanism, we need an emergent dynamic trust list for calculating the trust parties, thus, the CoT specifications require an initial effort on enrolling members automatically to adapt to the dynamic open environment. In this paper, we propose a Dynamic Trust Policy Language to support trust negotiation. The formal syntax of this language is presented in Backus Naur Form (BNF) based on the concept of role membership. We also systematically develop the Dynamic Trust Model (DTM) to allow Untrusted SP to join the existing CoT by trust negotiation. Finally, we identify the process and algorithm for communication between negotiation entities.

In the Web services environment, service level agreements (SLA) refer to mutually agreed understandings and expectations of service provision between service consumers and providers. Although management of SLA is critical to wide adoption of Web services technologies in the real world, support for it is very limited nowadays. There lacks adequate frameworks and technologies supporting various SLA operations. This paper presents an agent-based framework which utilises the agents' ability of negotiation, interaction, and cooperation to facilitate autonomous and flexible SLA management. Based on this framework, mechanisms for autonomous SLA formation, recovery, and profiling are proposed and discussed.

This paper reports innovative research aiming at supporting autonomous establishment and maintenance of service level agreements in order to guarantee end-to-end quality of service requirements for service composition provision. In this research, a set of interrelated service level agreements is established and maintained for a service composition, through autonomous agent negotiation. To enable this, an innovative framework is proposed in which agents on behalf of the service requestor and the service providers can negotiate service level agreements in a coordinated way. This framework also enables adaptive service level agreement re-negotiation in the dynamic and ever-changing service environment

As more and more organisations and institutions are moving towards the e-learning strategy, more and more disparate data are distributed by different e-learning systems. How to effectively use this vast amount of distributed data becomes a big challenge. This paper addresses this challenge and works out a new mechanism to implement data integration for e-learning. A workflow management system based (WFMS-based) data integration model is contributed to the e-learning

Workflow technology undoubtedly has been one of the most important domains of interest over the past decades, from both research and practice perspectives. However, problems such as potential poor performance, lack of reliability, limited scalability, insufficient user support, and unsatisfactory system openness are largely ignored. This research reveals that these problems are mainly caused by the mismatch between application nature, i.e., distributed, and system design, i.e., centralized management. Therefore, conventional approaches based on the client-server architecture have not addressed them properly so far. The authors abandon the dominating client-server architecture in supporting workflow because of its inherent limitations. Instead, the peer-to-peer infrastructure is used to provide genuinely decentralized workflow support, which removes the centralized data repository and control engine from the system. Consequently, both data and control are distributed so that workflow functions are fulfilled through the direct communication and coordination among the relevant peers. With the support of this approach, performance bottlenecks are likely to be eliminated while increased resilience to failure, enhanced scalability, and better user support are likely to be achieved. Moreover, this approach also provides a more open framework for service-oriented workflow over the Internet. This paper presents the authors' innovative decentralized workflow system design. The paper also covers the corresponding mechanisms for system functions and the Swinburne Decentralized Workflow prototype, which implements and demonstrates this design and functions

SwinDeW, a novel peer-to-peer based decentralised workflow, has been upgraded to SwinDeW-S, which supports Web service deployments and enactments to enhance system openness. To specify business process semantics, descriptions of input, output, precondition and effects, traditional workflow definition languages, such as extended XPDL, which was used in SwinDeW, have become insufficient. Even new service-oriented business process languages, such as BPEL4WS, are unable to support the full description of service profile either. In this paper, we propose a new framework based on OWLS, a semantic Web ontology language that leverages service discovery, invocation and coordination more effectively.