This paper presents a novel hallucination detection method based on the internal states and output probabilities of large language models (LLMs) to address the common issue of hallucinations in model-generated content. We designed a new detection framework that extracts internal features such as hidden layer states and word probabilities, and analyzes the output probability distribution to more accurately identify potential hallucinations. Experimental results show that our method outperforms traditional hallucination detection approaches across multiple evaluation metrics and performs well on our EpicQA dataset. This method offers a new perspective for hallucination detection and makes a significant contribution to improving the reliability of language models.

Personalized Federated Learning (PFL) is confronted with escalating security threats, yet existing defense strategies primarily concentrate on traditional federated learning, lacking robust defense mechanisms tailored for PFL. To fortify the robustness of PFL against stealthy malicious attacks, we propose an adaptive layered-trust robust defense mechanism, PFL-ALB. Firstly, we employ a layer gradient parameter similarity matrix to detect the malicious parameters of advanced stealthy backdoor attacks, and then conduct layer-wise robust aggregation on the server to enhance the robustness of the global model. Subsequently, we propose a client-adaptive personalized layering method, which adaptively partitions each client’s model into personalized and shared layers. This approach balances accuracy and robustness under heterogeneous data conditions while mitigating the impact of malicious attacks. Experimental results demonstrate that PFL-ALB significantly enhances robustness (with ASR remarkably reduced to within 1%-10%) under three types of advanced stealthy backdoor attacks and exhibits superior performance compared to existing defense schemes.

Abstract Federated learning (FL) enables collaborative training of global models among distributed clients without sharing local data. Secure aggregation, a new security primitive of FL, enhances the confidentiality of data and model parameters. Unfortunately, privacy-preserving (PP) FL is vulnerable to common poisoning attacks by Byzantine adversaries. Existing defense strategies mainly focus on identifying abnormal local gradients over plaintexts, which provides a weak privacy guarantee. In PPFL, adversaries can escape existing defenses by uploading encrypted poisonous gradients. In addition, most mainstream aggregation algorithms assume that clients’ local training data is uniformly distributed, Independent and Identically Distributed (IID), which is unrealistic for real-world FL scenarios where data are only stored on large-scale terminal devices. To address these issues, we propose PEAR, a PP aggregation strategy based on single key-dual server CKKS full homomorphic encryption in real-world distributed scenarios, which can resist encrypted poisoning attacks. Specifically, we use cosine similarity to measure the distance between encrypted gradients. Then, we propose a novel Byzantine-tolerance aggregation mechanism using cosine similarity, which includes trust score generation that can tolerate differentiated local gradients and a two-step weight generation method that considers both the degree of gradient deviation in direction and training data size. This mechanism can achieve robustness for both IID and non-IID data without compromising privacy. Our extensive evaluations for two typical poisoning attacks on different datasets show that PEAR is robust and effective in IID and non-IID data and outperforms existing mainstream Byzantine-robust algorithms, especially achieving 16.4% to 53.2% testing error rate reduction in non-IID settings with significant label distribution and quantity skew while maintaining the same efficiency as FedAvg.

With high resource utilization and flexibility, containers have gained widespread adoption across various computing environments. However, container security has emerged as a primary concern as container-based services grow rapidly. Identifying intrusions’ root cause and impact remains a foundational challenge in container security. Provenance reflects the causal relationships of events, which can significantly aid security personnel in analyzing container attacks. Despite existing provenance-based solutions providing extensive system information, there remains a lack of provenance systems specifically focused on container security. We present ConProv, which offers concise and precise provenance analysis of in--container activities, making it highly suitable for container security investigations. Through our analysis of container escape attack techniques, it is found that most attacks are caused by excessive permissions and incomplete file subsystem isolation. Based on this insight, we identified the key role that capabilities and file path attributes play in container provenance, which helps guide investigators to pinpoint suspicious events quickly. We developed a prototype implementation of ConProv and designed methods to capture these essential attributes accurately. Our evaluation shows that ConProv outperforms existing provenance systems in container attack investigations while incurring low overhead (<10%).

Data leakage is one of the most severe security threats that can compromise sensitive data through breaches or unauthorized access. Existing techniques usually adopt encryption or access control protection methods, but inevitably affects the data usability and introduce significant overhead. In this paper, we propose a novel technique for data leakage prevention in collaborative systems by dynamically broadening the deceptive attack surface. Our proposed technique offers an adaptive deception strategy that leverages historical user behaviors and current operations to generate deceptive data, and we developed an amplifying-based calculation method to enhance the accuracy of user trust degree evaluation. Furthermore, we introduce three deceptive indicators to evaluate our technique. Experimental results show that our technique can effectively prevent data leakage while preserving data usability and imposing minimal overhead to the system.

As an extension of cloud computing, edge computing provides storage and computing services at the network edge. Due to resource limitation of edge nodes, collaborative data offloading is usually utilized to offload overloaded data in the current node to adjacent nodes to ensure quality of service. In this case, the reputation mechanism is a crucial tool to select a reliable one from adjacent nodes to provide data storage service. However, existing works usually adopt the single source-based evaluation method, which is vulnerable to malicious manipulation and lacks objectivity. Meanwhile, the reputation of malicious nodes can be rapidly recovered, leading to a reduction in evaluation accuracy. To address these issues, we propose a secure blockchain-based edge nodes reputation scheme, combined with subjective evaluation result and objective monitoring values to provide a credible reputation. Specifically, to increase the malicious attack cost and limit reputation recovery speed, we design an Amplifying-based Reputation Calculation (ARC) mechanism to amplify the impact of malicious behaviors on reputation. In addition, we propose a Dynamic Miner Selection (DMS) algorithm to resist bookkeeping right attack from malicious infrastructure providers. Detailed analysis proves the security of our scheme and experiment results testify the effectiveness and efficiency.

Large language models (LLMs) demonstrate exceptional instruct-following ability to complete various downstream tasks.Although this impressive ability makes LLMs flexible task solvers, their performance in solving tasks also heavily relies on instructions.In this paper, we reveal that LLMs are over-sensitive to lexical variations in task instructions, even when the variations are imperceptible to humans.By providing models with neighborhood instructions, which are closely situated in the latent representation space and differ by only one semantically similar word, the performance on downstream tasks can be vastly different.Following this property, we propose a blackbox Combinatorial Optimization framework for Prompt Lexical Enhancement (COPLE).COPLE performs iterative lexical optimization according to the feedback from a batch of proxy tasks, using a search strategy related to word influence.Experiments show that even widelyused human-crafted prompts for current benchmarks suffer from the lexical sensitivity of models, and COPLE recovers the declined model ability in both instruct-following and solving downstream tasks.

Automatic detecting rumors on social media has become a challenging task. Previous studies focus on learning indicative clues from conversation threads for identifying rumorous information. However, these methods only model rumorous conversation threads from various views but fail to fuse multi-view features very well. In this paper, we propose a novel multi-view fusion framework for rumor representation learning and classification. It encodes the multiple views based on Graph Convolutional Networks (GCN) and leverages Convolutional Neural Networks (CNN) to capture the consistent and complementary information among all views and fuse them. Experimental results on two public datasets demonstrate that our method outperforms state-of-the-art approaches.

Federated learning decentralizes the learning process, yet it does not provide adequate privacy protection. Current countermeasures predominantly rely on Local Differential Privacy (LDP) techniques. While larger noise injection offers stronger privacy, it also leads to a degradation in model performance and necessitates additional training iterations. Existing methods struggle to strike a balance between user privacy, model usability, and training efficiency. To address this, we propose an adaptive noise scaling method grounded in mutual information. This method is designed to dynamically optimize the noise scale, thereby safeguarding user privacy, enhancing training efficiency, and ensuring model usability. Specifically, we first estimate the mutual information between user training data and gradient updates in each iteration using Mutual Information Neural Estimation (MINE). Subsequently, we propose to dynamically adjust the optimal noise scale in each round of federated learning’s local training, based on the estimated mutual information. Experimental results demonstrate that using mutual information to dynamically adjust the noise scale reduces the number of training iterations by over 50%, while maintaining the same level of user privacy and data model availability.

Automated surveillance cameras equipped with intelligent person detection systems are believed to have reached the maturity required for deployment in Intelligent Transport Systems, Intelligent Plants, and so on. However, recent studies have revealed that Deep Learning Neural Networks (DNN), on which mainstream person detection models are built, are vulnerable to adversarial attacks. Several methods have been proposed to generate adversarial patches that can evade person detectors. Nevertheless, these methods have limitations, as these adversarial patches are either restricted to being presented without any occlusion and placed in the center of the person, or they are too large in size and standing-out in pattern to be easily ignored by human eyes. Therefore, the adversarial patches in previous works did not consider both robustness and stealthiness when human posture changes and the patches are not in the center of person and partially occluded. In this paper, we propose AdvOcl that leverages the learned image manifold of the diffusion model to generate patterns that resemble one kind of the typical textures of daily clothes, such as common floral styles. Moreover, AdvOcl improved the adaptability and adversarial effectiveness by supporting changes in posture and partially occlusion during walking or running with warping and alignment module modeling deformation of clothes. Through extensive quantitative experiments, the results demonstrate the effectiveness of the proposed approach in generating more adversarially effective and naturalistic patterns in occluded scenarios compared to other state-of-the-art patch generation methods.

Mobile Edge Computing (MEC) has emerged as a distributed computing paradigm offering low-latency services to users. However, the distributed and intricate deployment inevitably makes it challenge to ensure the reliability of MEC services. Anomaly detection using the streaming data of MEC services is an essential way to address the challenge. In this paper, to improve the detection accuracy and efficiency, we propose an MTDF-Detection framework for MEC services, jointly extracting Multi-Timescale and Dimensional Feature (MTDF), including the long-term trend, periodic, short-term fluctuation and auxiliary parameters (e.g., system maintenance and offloading task). In this framework, to reduce the computing costs, we adopt a Bidirectional Simple Recurrent Unit (Bi-SRU) to obtain contextual feature; and we design an adaptive m-Sigma algorithm to determine the dynamic threshold with real-time streaming data. Extensive experiments are conducted on a real-world dataset, and the results demonstrate that the MTDF-Detection framework outperforms the state-of-the-art schemes in terms of accuracy and efficiency.

The recent advances of deep learning in various mobile and Internet-of-Things applications, coupled with the emergence of edge computing, have led to a strong trend of performing deep learning inference on the edge servers located physically close to the end devices. This trend presents the challenge of how to meet the quality-of-service requirements of inference tasks at the resource-constrained network edge, especially under variable or even bursty inference workloads. Solutions to this challenge have not yet been reported in the related literature. In the present paper, we tackle this challenge by means of workload-adaptive inference request scheduling: in different workload states, via adaptive inference request scheduling policies, different models with diverse model sizes can play different roles to maintain high-quality inference services. To implement this idea, we propose a request scheduling framework for general-purpose edge inference serving systems. Theoretically, we prove that, in our framework, the problem of optimizing the inference request scheduling policies can be formulated as a Markov decision process (MDP). To tackle such an MDP, we use reinforcement learning and propose a policy optimization approach. Through extensive experiments, we empirically demonstrate the effectiveness of our framework in the challenging practical case where the MDP is partially observable.

As cloud-native technologies continue to proliferate, fault diagnosis has become a critical aspect of online service systems. Operators tasked with fault diagnosis face the challenge of analyzing a wide range of monitoring metrics. These metrics often have missing data, adding complexity to the process. Their main goal is to locate faults among multiple components and find similar faults to develop effective solutions. However, prevailing methodologies fail to tightly integrate fault localization and fault correlation technologies, leading to suboptimal performance in root cause analysis. In this paper, we present a root cause analysis framework, SetRCA, that accurately localizes faults and offers interpretable identification of similar faults. To achieve this, we integrate the correlations between each pair of metrics with their temporal features for data interpolation using CP decomposition. Subsequently, the components in online service systems are ranked based on scores derived from the Personalized PageRank algorithm, using the filled data. Innovatively, the inclusion relationships between sets of abnormal metrics are employed to locate system faults. Ultimately, the solution is determined by examining the similarity between the current fault components and historical faults. An extensive study on two public datasets demonstrates the accuracy and interpretability of our proposed model.

With blockchain technology taking the world by storm, Hyperledger Fabric has large potential for application, but low throughput hinders its development. Especially Fabric endorsement phase serves as the upper process of transaction lifestyle, and its low throughput can diminish the performance of the entire system. In this paper, we focus on performance optimization in the endorsement phase. We design an efficient parallel endorsement node (EPEN) and implement the optimization in two steps. The first is parallel endorsement architecture, which improves the concurrency of endorsements and increases the scalability of peer nodes. Then we propose a load balancing algorithm based on consistent hash and design multilayer consistent hash load minimization (MCHLM) to load balance the chaincode containers and improve its utilization. In addition, we implement these optimizations scheme in Hyperledger Fabric 2.2 LTS and conduct a series of evaluation experiments. The experimental results demonstrated that EPEN improves Fabric system throughput by 204.3% and reduces transaction latency by 77.8%, with a 7.9% increase in CPU overhead.

The security and privacy of Vertical federated learning (VFL) deserve attention due to the computationally strong dependency between participants, which requires frequent and direct interactions. The existing Privacy-preserving (PP) VFL schemes are often limited by the model types supported, the communication cost and the number of participants. To alleviate this issue, we propose MK-FLFHNN, a novel PP framework for heterogeneous neural networks based on xMK-CKKS multi-key homomorphic encryption. The algorithm eliminates the limitation of traditional algorithms limited to generalized linear models and prevents the privacy leakage of shared information while solving the problem of potential leakage from the aggregated values of federated learning, adapting according to the number of participants and supporting flexible expansion to multi-party scenarios. Most importantly, for three-party and above scenarios, the framework is robust to collusion between K

Blockchain is widely applied in many applications. However, it faces many security risks. Unlike external attacks, the evildoing of internal members need more attentions in permissioned blockchain. We introduce the malicious resource consumption attack which seriously degrade the performance of permissioned blockchain system. To detect malicious resource consumption attacks, we propose MRC-Dec which applies a LSTM-AE model to analyze traffic between blockchain nodes, to determine whether the attacks happen. First, we construct the traffic dataset for attack detection by implementing two types of malicious resource consumption, namely useless endorsement and storage pollution on Fabric. Next in order not to be affected by the blockchain scale which means the number of nodes in blockchain, the traffic features are extracted between the node sets instead of between nodes. After feature extraction, a sequence of traffic features in temporal order is obtained, which is input to the LSTM-AE model. The LSTM-AE model learns the characteristic of normal traffic, and a threshold is set to determine normal and attack. The evaluation results show that MRC-Dec can find the malicious resource consumption attacks with high performance and can well adopt to the blockchain scale.

We present NadGPT, a transformer-based semi-supervised framework for network anomaly detection. It is known that transformer models are good at modeling long sequence data such as network traffic; however, without sufficient ground-truth labels, transformer models tend to suffer from over-fitting thus leading to inferior performance. Inspired by the recent success of GPT models in natural language processing (NLP), we propose a new auxiliary self-supervised task plugged to the backbone transformer, which enables GPT-like auto-regressive training on network traffic sequence without using ground-truth labels. Experiments demonstrate the proposed method greatly reduces the requirements of labels in network anomaly detection. For example, on ISCX 2012 dataset, given only 0.05% training labels our semi-supervised approach obtains nontrivial 81.7% (2-class) and 64.9% (5-class) Fl-scores on the validation set, which is far better than the supervised counterparts using the same training data. We hope our research could inspire more label-efficient methods in network traffic analysis.

Telemetry data is an important resource to detect anomaly of satellites in orbit. In recent years, the telemetry data-driven satellite anomaly detection has drawn great attention from academia and industries. However, in prior arts, the time-or frequency-domain data feature is usually separately utilized; and, to reduce the compute complexity, a small portion of data dimensions are usually selected from the telemetry data manually, leading to reduction in detection accuracy. Motivated by this, we propose a novel satellite telemetry data anomaly detection approach using high-dimension telemetry data, and the Multiple Factors and Co-Attention based LSTM (MFCA-LSTM) model. Specifically, to achieve an accurate prediction of telemetry sequence, we first propose the MFCA-LSTM model, jointly considering the time- and frequency-domain data feature, and the auxiliary information, e.g., telecommand and mission planning. Then, by using the MFCA-LSTM model, we construct a two-level anomaly detection framework to efficiently detect full-dimension data; and, to improve the accuracy rate and reduce the false alarm rate, we further propose an adaptive Tukey test algorithm to determine the dynamic thresholds. Finally, we perform extensive experiments based on two real-world datasets, and the results testify the effectiveness of our proposed framework.

In a permissioned blockchain, performance dictates its development, which is substantially influenced by its parameters. However, research on auto-tuning for better performance has somewhat stagnated because of the difficulty posed by distributed parameters; thus, it is possible only with difficulty to propose an effective auto-tuning optimization scheme. To alleviate this issue, we lay a solid basis for our research by first exploring the relationship between parameters and performance in Hyperledger Fabric, a permissioned blockchain, and we propose Athena, a Fabric-based auto-tuning system that can automatically provide parameter configurations for optimal performance. The key of Athena is designing a new Permissioned Blockchain Multi-Agent Deep Deterministic Policy Gradient (PB-MADDPG) to realize heterogeneous parameter-tuning optimization of different types of nodes in Fabric. Moreover, we select parameters with the most significant impact on accelerating recommendation. In its application to Fabric, a typical permissioned blockchain system, with 12 peers and 7 orderers, Athena achieves a throughput improvement of 470.45% and a latency reduction of 75.66% over the default configuration. Compared with the most advanced tuning schemes (CDBTune, Qtune, and ResTune), our method is competitive in terms of throughput and latency.

Robust keypoint detection on omnidirectional images against large perspective variations, is a key problem in many computer vision tasks. In this paper, we propose a perspectively equivariant keypoint learning framework named OmniKL for addressing this problem. Specifically, the framework is composed of a perspective module and a spherical module, each one including a keypoint detector specific to the type of the input image and a shared descriptor providing uniform description for omnidirectional and perspective images. In these detectors, we propose a differentiable candidate position sorting operation for localizing keypoints, which directly sorts the scores of the candidate positions in a differentiable manner and returns the globally top-K keypoints on the image. This approach does not break the differentiability of the two modules, thus they are end-to-end trainable. Moreover, we design a novel training strategy combining the self-supervised and co-supervised methods to train the framework without any labeled data. Extensive experiments on synthetic and real-world 360° image datasets demonstrate the effectiveness of OmniKL in detecting perspectively equivariant keypoints on omnidirectional images. Our source code are available online at https://github.com/vandeppce/sphkpt.

Mobile edge computing (MEC), extending computing services from cloud to edge, is recognized as one of key pillars to facilitate real-time services and tackle backhaul bottleneck. However, it is not economically efficient to attach intensive security appliances to every MEC node to defend application-level DDoS attacks and ensure the availability of services. Thus, we explore the elasticity of security defense among MEC nodes by proposing a COoperative DEfense (CODE) framework for MEC, referred to asCODE4MEC. CODE4MEC aims to adapt to traffic changes by coordinating container-carried defensive resources among cooperative MEC nodes in an automatic way. Towards this aim, we propose four control plane functions to enable a life-cycle management for CODE4MEC, namely, CODE triggering, scheduling, coordination and releasing. However, an effective CODE4MEC requires non-trivial algorithmic schemes, in particular for CODE scheduling and coordination functions. We thus design an online combinatorial auction mechanism for real-time CODE scheduling, and prove a tighter performance bound relative to prior arts. As for CODE coordination, a flow-based traffic and context information coordination scheme is proposed to enable classical defense schemes to work properly and efficiently. Finally, using a combination of real testbed and simulation evaluations, we validate the effectiveness of CODE4MEC.

Lightweight virtualization technology represented by the container is developing rapidly and plays an increasingly important role in cloud computing. Container technology is efficient and flexible, but the kernel-sharing property also means its isolation is incomplete, making multi-tenancy container clouds vulnerable to co-resident attacks. The existing placement strategy either only considers the resource allocation problem or only considers the co-resident security problem of the virtualization technology on the same host. In this paper, we present SecCPS, a Secure Container Placement Strategy using deep reinforcement learning in a typical cloud scene. SecCPS learns to find the optimal placement to mitigate co-resident threats between containers running on virtual machines. In the design of SecCPS, we (1) present the challenges of securely placing containers running on virtual machines and establish metrics to describe co-residence in container clouds; (2) develop a secure container placement strategy using deep reinforcement learning as a preventive measure for co-residence; (3) implement the strategy and evaluate its effectiveness and scalability. The results show that SecCPS can effectively reduce co-residence compared with existing strategies and is scalable and flexible to large-scale container deployment scenarios.

The open resolver, which provides resolution services for the public without verifying user identities, is a critical component of the Domain Name System (DNS). In reality, users have natural trust in public resolution services, which is unilateral and unreliable due to the existence of open resolvers which tamper with the user’s DNS requests to the wrong IP addresses on the Internet. This tampering behavior has strong concealment which is difficult to be detected by users or security researchers. Therefore, it is exactly essential to discover such malicious behavior in time when combating cyber attackers. The traditional solution is to use the IP addresses of malicious open resolvers for blacklist defense, which is simple to implement but has disadvantages of false positives and false negatives. In this paper, we propose a method based on deep learning, namely Byte-level Autoencoder, to implement the detection of malicious open resolvers without the complex manual feature extraction process. Our work is the first study to detect malicious open resolvers in this field, based on the similarity of normal DNS messages. Experimental results show that our method has a high accuracy of 98.83%, a high precision of 97.84% and a low false positive rate of 0.11%, which verifies the effectiveness of our method.

Aiming at the urgent need for a cross-domain authentication scheme with low computational cost, low latency, and high security in the edge computing environment, this paper proposes a blockchain-based cross-domain authentication protocol. In this protocol, the IoT devices in the edge computing environment themselves control the generation, encrypted storage, registration, use or cancellation of their identities, and the authenticity and credibility of these identities can be guaranteed through a trusted identity checking mechanism. The public information of these identities is shared among edge nodes of different domains using the consensus mechanism of blockchain. IoT devices can perform cross-domain authentication at the edge. The authentication process not only makes use of the advantages of low latency of edge computing, but also minimizes the disclosure of detailed identity information. Security analysis shows that the protocol can resist common attacks such as DDoS Attacks and Impersonation Attacks. Compared with several previous cross-domain authentication schemes, our protocol is more secure. Besides, this protocol has the advantage of low computational cost, suitable for low-performance IoT devices.

Hardware-assisted virtualization is widely adopted in cloud computing and desktop platforms, significantly enhancing the security and efficiency of full virtualization systems by dividing multiple guest operating systems (OSes) and providing isolation between guest OSes and host OS. Thus, malware is usually analyzed in a guest OS to prevent the host OS from being compromised. However, an advanced malware will deliberately masquerade as a benign program when it detects that it is in a virtualized environment. The ideal goal of virtualization is to be utterly transparent to the guest processes, i.e., a guest process cannot be aware that it runs in a virtualized environment. Nowadays, although hardware-assisted virtualization detection is challenging, we present three novel approaches that can be leveraged to detect hardware-assisted virtualization. Our detection approaches are mainly based on the following features: i) The available CPU instruction sets are different in native and virtualized environments; ii) Modification to specific control register flag has different effects in native and virtualized environments; iii) The physical addresses in native and virtualized environments have different effects on the eviction of the level 2 CPU cache. We have conducted intensive experiments in both native and cloud environments. The experimental results show that our approaches can effectively detect the existence of hardware-assisted virtualization.

The application of deep neural networks (DNNs) on 360-degree images has achieved remarkable progress in the recent years. However, DNNs have been demonstrated to be vulnerable to well-crafted adversarial examples, which may trigger severe safety problems in the real-world applications based on 360-degree images. In this paper, we propose an adversarial attack targeting spherical images, called 360-attactk, that transfers adversarial perturbations from perspective-view (PV) images to a final adversarial spherical image. Given a target spherical image, we first represent it with a set of planar PV images, and then perform 2D attacks on them to obtain adversarial PV images. Considering the issue of the projective distortion between spherical and PV images, we propose a distortion-aware attack to reduce the negative impact of distortion on attack. Moreover, to reconstruct the final adversarial spherical image with high aggressiveness, we calculate the spherical saliency map with a novel spherical spectrum method and next propose a saliency-aware fusion strategy that merges multiple inverse perspective projections for the same position on the spherical image. Extensive experimental results show that 360-attack is effective for disturbing spherical images in the black-box setting. Our attack also proves the presence of adversarial transferability from Z2 to SO(3) groups.

As essential work in IT operations, anomaly localization, aiming to identify the affected scope of Internet infrastructure once an anomaly alarm occurs, is challenging due to the huge search space. The existing solutions usually show limited performances in the CDN scenario since they take the desirable assumptions that do not match with the practical anomaly pattern features. To address this issue, in this paper, we propose RAPMiner, which first uses a classification power-based redundant attribute deletion to prune the non-root cause attribute combinations, and then adopts an anomaly confidence-guided layer-by-layer top-down search to avoid searching for anomaly but non-root patterns. Both of them are effective in narrowing the search space. Experimental results show that RAPMiner can achieve comparable performance with the SOTA approach on the published Squeeze dataset according to F1-score and efficiency, as well as the best RC@k with stable parameter sensitivity on the RAPMD.

The safety of Deep Neural Networks (DNNs) processing omnidirectional images (ODIs) is an under-researched topic. In this paper, we propose a novel sparse attack, named Single-Perspective (SP) Attack, towards fooling these models by perturbing only one perspective image (PI) rendered from the target ODI. The attack is launched from the perspective domain, and finally the perturbation is transferred to the original ODI. To this end, we propose an effective PI position searching algorithm based on Bayesian Optimization, and then corrupt the PI centered on the desirable position with unconstrained/constrained perturbations. Extensive experiments on synthetic and real-world omnidirectional datasets demonstrate that SP Attack can overcome the projection deformation of ODIs, and mislead the neural networks by limiting the perturbations in a single patch on the target ODI.

Depth estimation for panorama is a key part of 3D scene understanding, and adopting discriminative models is the most common solution. However, due to the rectangular convolution kernel, these existing learning methods cannot efficiently extract the distorted features in panoramas. To this end, we propose OmniVAE, a generative model based on Conditional Variational Auto-Encoder (CVAE) and von Mises-Fisher (vMF) distribution, to strengthen the exclusive generative ability for spherical signals by mapping panoramas to hypersphere space. Further, to alleviate the side effects of manifold-mismatching caused by non-planar distribution, we put forward the Atypical Receptive Field (ARF) module to slightly shift the receptive field of the network and even take the distribution difference into account in the reconstruction loss. The quantitative and qualitative evaluations are performed on real-world and synthetic datasets, and the results show that OmniVAE outperforms the state-of-the-art methods.

Object detection methods for perspective images have proven increasingly efficient, but the techniques for equirectangular projection (ERP) panoramas from inherently spherical imaging cannot still achieve satisfactory performance. Due to the various degrees of distortion at different pixel locations, current algorithms cannot adapt to the changes in shape and contour caused by stretching, which results in performance degradation when migrating them from perspective images to spherical ones. In this paper, we improve the network for panorama object detection and introduce the cube-domain information with discontinuity but low distortion to correct the panorama features. Unlike previous works, we consider the impact of semantic discontinuity from all tangent planes instead of overlaying features when needed. Considering the six facets as unified, i.e., six-to-one for extraction, the proposed Facet-Link module enhances the long-range sensing capability at the facet level in the frequency domain. Moreover, the position alignment packs different facets, i.e., six-to-one for calibration, to preserve more global signals during the correction stage, which establishes semantic pathways for feature interactions between panorama and cubemap in the two dimensions, facet-facet and cube-pano, respectively. Extensive experiments on synthetic and real-world datasets verify the effectiveness and robustness of our proposed method.

To conduct service quality management of industry devices or Internet infrastructures, various deep learning approaches have been used for extracting the normal patterns of multivariate Key Performance Indicators (KPIs) for unsupervised anomaly detection. However, in the scenario of Content Delivery Networks (CDN), KPIs that belong to diverse websites usually exhibit various structures at different timesteps and show the non-stationary sequential relationship between them, which is extremely difficult for the existing deep learning approaches to characterize and identify anomalies. To address this issue, we propose a switching Gaussian mixture variational recurrent neural network (SGmVRNN) suitable for multivariate CDN KPIs. Specifically, SGmVRNN introduces the variational recurrent structure and assigns its latent variables into a mixture Gaussian distribution to model complex KPI time series and capture the diversely structural and dynamical characteristics within them, while in the next step it incorporates a switching mechanism to characterize these diversities, thus learning richer representations of KPIs. For efficient inference, we develop an upward-downward autoencoding inference method which combines the bottom-up likelihood and up-bottom prior information of the parameters for accurate posterior approximation. Extensive experiments on real-world data show that SGmVRNN significantly outperforms the state-of-the-art approaches according to F1-score on CDN KPIs from diverse websites.

As a distributed ledger technology, the addition of new members in permissioned blockchain is usually composed of several steps among distributed nodes. The addition can not be considered successful until all of the steps are completed. In other words, these steps are an atomic operation. However, there is no solution for the atomic operation in existing permissioned blockchain, leading to an inconsistent state when the addition of new members is partially completed. To implement the atomic member addition in permissioned blockchain, we propose a method targeting at the atomic addition of new members based on distributed and autonomous rollback. After member addition starts, distributed nodes of existing members detect the new node and decide whether to rollback or not, instead of getting commands from the coordinator. After deciding to rollback, a new configuration block is added to achieve rollback of the uncompleted member addition. In order for the new configuration block to pass the policy validation of orderers, we set a rollback mode for orderers. The evaluation results show that our method can actually implement atomic member addition and has little impact on performance.

Abstract Rotational-XOR cryptanalysis is a very recent technique for ARX ciphers. In this paper, the probability propagation formula of RX-cryptanalysis in modular addition is extended, and the calculation of RX-difference probability for any rotation parameter ($0

Abstract Hunting the advanced threats hidden in the enterprise networks has always been a complex and difficult task. Due to the variety of attacking means, it is difficult for traditional security systems to detect threats. Most existing methods analyze log records, but the amount of log records generated every day is very large. How to find the information related to the attack events quickly and effectively from massive data streams is an important problem. Considering that the knowledge graph can be used for automatic relation calculation and complex relation analysis, and can get relatively fast feedback, our work proposes to construct the knowledge graph based on kernel audit records, which fully considers the global correlation among entities observed in audit logs. We design the construction and application process of knowledge graph, which can be applied to actual threat hunting activities. Then we explore different ways to use the constructed knowledge graph for hunting actual threats in detail. Finally, we implement a LAN-wide hunting system which is convenient and flexible for security analysts. Evaluations based on the adversarial engagement designed by DARPA prove that our platform can effectively hunt sophisticated threats, quickly restore the attack path or assess the impact of attack.

Migration-based Dynamic Platform (MDP) technique, a type of Moving Target Defense (MTD) techniques, defends against sophisticated cyber-attacks by randomly and dynamically selecting a platform for executing service/job. Security defense mechanisms protect service/job usually at the cost of degrading its performance. Therefore, it is valuable to make a trade-off between service/job security and its performance. However, previous researches on MTD techniques either focused on analyzing MTD effectiveness of protecting service/job or studied service/job performance with the assumption that attacks on service/job make no influence on its execution. This article aims to apply analytical modeling techniques to investigate the impact of MDP technique on job completion time in a system under attack. We use Stochastic Reward Nets (SRNs) to develop a Markov chain-based model for capturing typical behaviors of the adversary, the vulnerable system and a job. The formulas are derived for calculating the metrics of interest. Numerical analysis is conducted to study the impact of key parameters on job completion time and job security loss.

With the capability of trading accuracy for latency on-the-fly, the technique of adaptive early-exit inference has emerged as a promising line of research to accelerate the deep learning inference. However, studies in this line of research commonly use a group of thresholds to control the accuracy-latency trade-off, where a thorough and general methodology on how to determine these thresholds has not been conducted yet, especially with regard to the common requirements of average inference latency. To address this issue and enable latency-aware adaptive early-exit inference, in the present paper, we approximately formulate the threshold determination problem of finding the accuracy-maximum threshold setting that meets a given average latency requirement, and then propose a threshold determination method to tackle our formulated non-convex problem. Theoretically, we prove that, for certain parameter settings, our method finds an approximate stationary point of the formulated problem. Empirically, on top of various models across multiple datasets (CIFAR-10, CIFAR-100, ImageNet and two time-series datasets), we show that our method can well handle the average latency requirements, and consistently finds good threshold settings in negligible time.

ASR (Automatic Speech Recognition) technology is a key technology for human-computer interaction. Especially the DNN models of wake-up-word speech recognition, which enables the smart device to recognize wake-up words spoken by users when they are in the sleep or lock screen state, allowing the device to directly enter the wait command state, and start the first step of voice interaction. ASR technology no wonder provides great convenience for people's daily life, but it's security problem has always been a hot topic of further research. The rapid development of ASR models has made these models very vulnerable which seriously affect their performance in real scenarios. This paper proposes a new backdoor attack method TNN (Trojan Neural Network) for deep learning models in voice wake-up scenarios. The attacker leaves backdoor in the deep learning model of the ASR. Besides specific wakeup words, attackers can also use other words to force the device to wake up and get the IoT smart device's highest privileges. And when the smart device is in the awake state, any audio containing a particular vocabulary will be recognized as a specific command and executed. In this papaer, we propose a novel method to attack ASR model, and without affecting the performance of clean samples, by applying the attack method, the success rate in compulsory recognition of specific words can be up to 100%. The experimental results prove that our attack method is very effective and poses a great security problem of the voice-interactive IoT device.

DNS open resolvers represent key components of Internet networks, providing recursive resolution services for all users across the Internet. Monitoring operational profiles of the open resolvers is crucial in analyzing cyber security threats. However, due to the lack of authentication or authorization between users and DNS servers, malicious attackers can exploit these vulnerabilities potentially. In this paper, we design an efficient long-term scanning scheme for the entire IPv4 address space, and approximately 1.8 million open resolvers on the network come into light. By investigating the response packets, we observe that some of them are working in a non-standard way. Moreover, many resolvers respond to user requests with incorrect (even malicious) information. In addition, we discover the existence of ghost resolvers, which cache domain names that have been cleared.

As one type of omnidirectional projection, fisheye images have been widely used in automatic driving and visual surveillance. However, they cannot be processed well by the traditional algorithms designed for the planar rectilinear images since they usually suffer from severe geometric distortion during image formation. In this paper, the conventional face detection algorithm is enhanced to fit the fisheye images via combining with the spherical convolution block by learning rotation-invariant features from the spherical domain. The learned features from both planar and spherical domains are subsequently mixed by the spatial attention mechanism. Consequently, the whole network can automatically learn the distorted features directly from different positions on the target image. Experimental results verify that our network can detect distorted faces on fisheye images effectively and maintain the performance on traditional planar images.

Cloud computing provides a shared pool of configurable computing resources and significantly improves the utilization of computing resources, but it also introduces security threats. We focus on the virtual machine (VM) co-residency, which allows an attacker to launch cross- VM attacks against target VMs. To tackle this problem, we propose a secure and efficient VM allocation strategy to reduce the cross- VM attack threats while ensuring the efficiency of the cloud data center. First, we establish several metrics related to security and efficiency for the cloud data center. Then, we establish a constrained optimization model. Next, we allocate and migrate VMs based on typical suspicious or vulnerable VM features, and solve the optimization problem through our improved NSGA-II allocation. Finally, we implement our allocation strategy and conduct intensive experiments. The experimental results show that our allocation strategy performs better than the existing stratezies and orovides cloud vendors with tradeoff solutions.

With the rapid advancements in Augmented Reality, the number of AR users is gradually increasing and the multiuser AR ecosystem is on the rise. Currently, AR applications usually present results without limitations, which causes great latent danger to users, so it is necessary to apply strategies to ensure the safe output of AR. Due to the environmental diversities among the distributed users, the traditional approaches designed for single-user AR are not efficient for multi-user AR applications. Considering the characteristics of multi-user AR scenarios, we propose a multi-user AR output strategy model based on Federated Reinforcement Learning. With the device-fog-cloud hierarchical architecture, the proposed models are obtained first by Reinforcement Learning on users' devices, and are then hierarchically aggregated on the fog nodes and cloud server. We performed extensive AR simulations in Unity and obtained the results that show our method can avoid several security problems existent in multi-user AR applications.

Content Delivery Networks (CDNs) are critical for providing good user experience of cloud services. CDN providers typically collect various multivariate Key Performance Indicators (KPIs) time series to monitor and diagnose system performance. State-of-the-art anomaly detection methods mostly use deep learning to extract the normal patterns of data, due to its superior performance. However, KPI data usually exhibit non-additive Gaussian noise, which makes it difficult for deep learning models to learn the normal patterns, resulting in degraded performance in anomaly detection. In this paper, we propose a robust and noise-resilient anomaly detection mechanism using multivariate KPIs. Our key insight is that different KPIs are constrained by certain time-invariant characteristics of the underlying system, and that explicitly modelling such invariance may help resist noise in the data. We thus propose a novel anomaly detection method called SDFVAE, short for Static and Dynamic Factorized VAE, that learns the representations of KPIs by explicitly factorizing the latent variables into dynamic and static parts. Extensive experiments using real-world data show that SDFVAE achieves a F1-score ranging from 0.92 to 0.99 on both regular and noisy dataset, outperforming state-of-the-art methods by a large margin.

Abstract Long-term prediction is still a difficult problem in data mining. People usually use various kinds of methods of Recurrent Neural Network to predict. However, with the increase of the prediction step, the accuracy of prediction decreases rapidly. In order to improve the accuracy of long-term prediction,we propose a framework Variational Auto-Encoder Conditional Generative Adversarial Network(VAECGAN). Our model is divided into three parts. The first part is the encoder net, which can encode the exogenous sequence into latent space vectors and fully save the information carried by the exogenous sequence. The second part is the generator net which is responsible for generating prediction data. In the third part, the discriminator net is used to classify and feedback, adjust data generation and improve prediction accuracy. Finally, extensive empirical studies tested with five real-world datasets (NASDAQ, SML, Energy, EEG,KDDCUP)demonstrate the effectiveness and robustness of our proposed approach.

Cyber–Physical–Social Systems are frequently prescribed for providing valuable information on personalized services . The foundation of these services is big data which must be trustily collected and efficiently processed. Though High Performance Computing and Communication technique makes great contributions to addressing the issue of data processing, its effectiveness still relies on the veracity of data generated from Internet of Things (IoT) devices. Nevertheless, IoT devices, as basic production facilities to ensure data’s security, are unable to deploy expensive security extensions. Consequently, it causes the implementation of the task sandboxing, the fundamental security mechanism in Real-Time Operating Systems (RTOSs), much simpler and more vulnerable. In this paper, we take ARM Mbed uVisor as an example system, utilizing hypervisor-based task sandboxing mechanisms, and presents three new findings: First, we discover vulnerabilities against Mbed task sandboxing, which can be exploited to compromise system-maintained data structure to manipulate any tasks’ data. Second, we present LIPS (Lightweight Intra-Mode Privilege Separation), building a special protection domain to isolate particular system-maintained data structures. Finally, thorough evaluation and experimental tests show the efficiency of LIPS to defeat these attacks, with small runtime overheads and good portability.

Similar to conventional video, the increasingly popular 360 virtual reality (VR) video requires copyright protection mechanisms. The classic approach for copyright protection is the introduction of a digital watermark into the video sequence. Due to the nature of spherical panorama, traditional watermarking schemes that are dedicated to planar media cannot work efficiently for 360 VR video. In this article, we propose a spherical wavelet watermarking scheme to accommodate 360 VR video. With our scheme, the watermark is first embedded into the spherical wavelet transform domain of the 360 VR video. The spherical geometry of the 360 VR video is used as the host space for the watermark so that the proposed watermarking scheme is compatible with the multiple projection formats of 360 VR video. Second, the just noticeable difference model, suitable for head-mounted displays (HMDs), is used to control the imperceptibility of the watermark on the viewport. Third, besides detecting the watermark from the spherical projection, the proposed watermarking scheme also supports detecting watermarks robustly from the viewport projection. The watermark in the spherical domain can protect not only the 360 VR video but also its corresponding viewports. The experimental results show that the embedded watermarks are reliably extracted both from the spherical and the viewport projections of the 360 VR video, and the robustness of the proposed scheme to various copyright attacks is significantly better than that of the competing planar-domain approaches when detecting the watermark from viewport projection.

Although deep neural networks have demonstrated exceptional performance in substantial computer vision tasks, they can be easily confused by carefully generated adversarial examples. Via a novel technique we call activation visualization, the particular characteristics of adversarial examples are analyzed in this paper. Observing that the dominant features of adversarial examples are distributed over a high-dimensional space, we propose a defense framework named RegionSparse that projects the images into a low-dimensional space to remove the influence of the adversarial perturbations on the performance of deep neural networks. In RegionSparse, after training a robust global dictionary, the region where pixels are highly related to classification is firstly located by an object localization mechanism, then the sparse coding is performed on the located object region, together with a perturbation suppression for the remaining region. Extensive experiments on ImageNet dataset for gray-box, black-box, and transferred attacks are performed and the results show that RegionSparse can eliminate up to 90% attacks delivered by strong attacks including Momentum Iterative Fast Gradient Sign Method and Carlini-Wagner's L2attack.

CDN (Content Delivery Network) has become an important infrastructure of the Internet. However, building an anomaly detection system to monitor and guarantee CDN service quality is non-trivial. Current anomaly detection system usually suffers from undesirable performance in terms of high rate of false positive and false negative, which consequently impacts on its practical deployment. Identifying the root cause of a false detection is critical for diagnosing and improving the performance of anomaly detection. In this paper, we propose a novel feedback mechanism for prediction-based anomaly detection in CDN . Specifically, we introduce a carefully-designed metric named Fittingscore to diagnose whether the prediction model can fit the data well. Further, a threshold adjustment mechanism is proposed to dynamically adjust the thresholds of residual errors. Extensive experiments employing a three-month real CDN dataset collected from a top ISP-operated CDN in China show our proposed method can significantly improve the performance of anomaly detection.

In the past decades, various approaches have been proposed to address the time series prediction problem, among which nonlinear autoregressive exogenous (NARX) models achieve great progresses in one-step time prediction. Although NARX models are capable of capturing long-term dependence of the time series data, the impact of associated attributes lacks enough attention. To cope with this issue, in this paper we propose a Multi-Attention algorithm based Recurrent Neural Network (RNN) to perform multivariate time series forecasting. In the first stage, given a raw multivariate time series segment, we obtain both relevant encoder hidden state and encoder hidden state of the associated attribute by employing input-attention and self-attention respectively. In the second stage, we use temporal-convolution-attention neural network to process the encoder hidden states and capture long-range temporal patterns. Finally, extensive empirical studies tested with four real world datasets (NASDAQ100, SML2010, Gas Sensor Array Temperature Modulation and Air Quality) demonstrate the effectiveness and robustness of our proposed approach.

A context-aware hook is a piece of code. It checks context-aware user privacy policy before some sensitive operations happen. We propose Prihook to address specific context-aware user privacy concerns through putting specific context-aware hooks. We design User Privacy Preference Table (UPPT) to help a user express his privacy concerns and propose a mapping from the words in the UPPT lexicon to the methods in the Potential Method Set. With this mapping, Prihook is able to (a) select a specific set of methods; and (b) generate and place hooks automatically. Hence, the hook placement in Prihook is personalized. We test Prihook separately on 6 typical UPPTs representing 6 kinds of resource-sensitive UPPTs, and no user privacy violation is found. The experimental results show that the hooks placed by PriHook have small runtime overhead.

Bring-Your-Own-Device (BYOD) has been widely viewed as a definite trend among enterprises in which employees bring and use their personal smartphones for work. Despite the perceived opportunities of increasing productivity and reducing costs, BYOD raises severe security and privacy concerns: the corporate networks and data are directly exposed to malware apps running on the personal smartphones. This highlights the necessity for performing real-time mobile malware detection in BYOD environments. Deep learning seems to be a natural choice to handle such detection, due to its state-of-the-art detection effectiveness. However, deep learning inference is usually too computationally complex for resource-constrained smartphones, and the communication overhead of cloud-based inference may be unacceptable. As a result, it is hard to seek the tradeoff between the real-time demand and optimality of detection accuracy. In this paper, we tackle this issue by proposing an endedge coordinated inference approach that can support highlyaccurate and average latency guaranteed malware detection. Our proposed approach integrates the early-exit and model partitioning methods to allow fast, correct and smartphonelocalized inference to occur frequently. Extensive evaluations are carried out, demonstrating that our proposed approach offers a good compromise between detection accuracy and efficiency.

Inference based on deep learning models is usually implemented by exposing sensitive user data to the outside models, which of course gives rise to acute privacy concerns. To deal with these concerns, Donget al.recently proposed an approach, namely the dropping-activation-outputs (DAO) first layer. This approach was claimed to be a non-invertible transformation, such that the privacy of user data could not be compromised. However, In this paper, we prove that the DAO first layer, in fact, can generally be inverted, and hence fails to preserve privacy. We also provide a countermeasure against the privacy vulnerabilities that we examined.

The development of Internet of Things (IoT) dramatically facilitates the integration of computing systems with the physical world. However, as IoT devices are more easy to compromise than desktop computers, cybercriminals have founded IoT-based botnets to launch Distributed Denial of Service (DDoS) attacks with unprecedented traffic volume. To mitigate the damages associated with these attacks, the detection of IoT-based botnet has to preempt the command and control (C&C) communication to prevent the delivery of the attack codes. Motivated by the extensively implementation of domain generation algorithm in botnets, in this article, we propose ConnSpoiler, a lightweight system that detects IoT-based botnets by identifying the stream of algorithmically generated domains (AGDs) in a fast way. ConnSpoiler only needs negligible system resources to take effect and thus can execute well on the resource-restraint IoT devices. By outfitting a powerful statistical algorithm, i.e., threshold random walk, ConnSpoiler has a high probability (about 94%) of detecting infection before the compromised devices connect C&C servers, which can help to prevent the succeeding attacks. Moreover, ConnSpoiler only requires the benign domains to take effect and therefore does not need extra effort to label malicious samples for training phase. We evaluate ConnSpoiler based on real-world DNS traffics collected from two different large ISP networks and show that it accurately identifies devices that are compromised by unknown botnets.

Software defined networking is attracting extensive attention to achieve better network performance through flexible flow path control. However, traditional OpenFlow-based forwarding method faces practical challenges such as limited flow table size and dynamic flow path setup. In this work we propose a scalable and flexible path control schema based on source routing to address those problems through pre-installing flow paths into the data plane and inserting path information into the packet header at the network edge. To reduce the flow table overhead, we assign an ID to each path and aggregate IDs by wildcards. We formulate the path ID assignment problem and decompose it into the link ID assignment problem, which is solved by our proposed heuristic algorithm based on vertex coloring and topological potential. Extensive simulations on various topologies show that our proposed algorithm can reach the optimal solutions in most topologies within the time limit, and our path control schema can save more than 98% rules compared with traditional OpenFlow-SDN method and has good universality. In addition, our method can achieve better performance in terms of dynamic flow path setup due to the characteristic of source routing.

Software-Defined Networking (SDN) controllers are deployed as a cluster in large-scale networks, for high availability and scalability. A device (e.g., switch) is connected to multiple controllers in cluster while assigned with one master controller, and the controller with master role is only permitted to manage the device. Therefore, the master controller assignment can affect the network throughput seriously. In this paper, we first study the assignment strategy of two well-known SDN platforms (i.e., OpenDayLight and Open Network Operating System) as well as the assignment mechanisms in the existing literature, analyzing their deficiencies. Meanwhile, we present an adaptive controller assignment so as to maximize the network throughput under the fluctuating network environment. We formulate this problem as an Integer Linear Program and propose an algorithm based on Ant Colony optimization to solve it efficiently. Extensive experiments validate that our solution is superior to other existing mechanisms in terms of network throughput and load balancing.

Aiming at various issues, such as performance, load-balance and robustness, of Software-Defined Networking (SDN) controller cluster, several deployment strategies have been proposed. As a supplement, our work delivers a cost-effective multicontroller deployment strategy in terms of economic benefits. In this paper, we formalize a Cost-optimized Multi-Controller Deployment (CO-MCD) problem by concerning the controller's deployment cost and the network service's delay cost. Meanwhile, we characterize the communication between the controller and the switch using a queuing system, and design an algorithm to determine the optimal deployment in the specified environment. Simulation results validate that the proposed algorithm can always obtain a deployment solution which minimizes the economic cost of the entire SDN network. This work aims at being a useful primer to provide insights regarding the economic impact of multiple controllers in the realistic SDN deployment, so that network owners plan their investments more rationally.

Mobile edge computing (MEC), as an enabling paradigm allowing mobile services to be performed at the edge of mobile networks, has been commonly expected to facilitate real-time services and offload backhaul traffic. However, the security issues raised by innovations in networks always hesitate us to embrace their benefits, and so MEC does. DDoS attacks originating from massive mobile devices in 5G, especially the vulnerable internet-of-things devices, is an unavoidable threat for MEC services. Unfortunately, each MEC node is hard to maintain service availability in the wake of DDoS attacks, owing to its limited hardware resources for defense. Therefore, we are motivated to study the cooperative defense against DDoS attacks for MEC, where defense resources can be shared between MEC nodes. Specifically, we purpose a global orchestration (GO) mechanism to make full use of freedom degrees of cooperative defense with respect to the number of cooperative participants and the amount of cooperative resource. In the process of designing the GO mechanism, we formulate the optimization problem of GO, and exploit the bucket elimination algorithm to find the optimal solutions. To make the GO mechanism practically usable, we propose a scalable approximation algorithm based on the mini-bucket elimination algorithm. Extensive simulations are carried out to validate the effectiveness of GO.

In the Software-Defined Networking (SDN) philosophy, a logically centralized control plane remotely instructs distributed network devices to forward packets over control channel. However, such a centralized design makes the control channel a bottleneck due to bandwidth fatigue, which seriously threatens the availability of the network. Existing studies economize control channel bandwidth at the expense of the visibility of most or mice flows. This paper presents EFastLane, an effective solution for bandwidth-efficient flow setup without sacrificing any flow visibility. EFastLane advocates that the controller only sends the entire processing rule to an intermediate switch of the forwarding path, and then the rule is installed bidirectionally along the path. Besides, we propose two algorithms to locate such a target switch to ensure that all switches on the path install the forwarding rule before receiving packets. Simulation experiments validate that EFastLane saves over 70% of control channel bandwidth compared to traditional SDN, while introducing the negligible flow setup time and traffic delay.

In the context of Advanced Persistent Threat-s (APTs), system audit log-based intrusion forensics has been proposed to carry out attack investigation. System audit log is highly suitable for intrusion forensics because it records the interactions among system entities in detail. However, system audit log has a fatal shortcoming due to its massive growth of log size. To address this issue, this paper proposes a compression scheme for system audit log named T-Tracker. Firstly, T-Tracker detects the events that communicate with external data sources and generates the initial taint set. Then it tracks the diffusion of the taint according to the audit log. By retaining the events on diffusion path only, we can achieve log compression. Our evaluation with different system workloads and attack cases demonstrates that our approach can achieve significant log compression without affecting the accuracy of intrusion forensics.

Table-overflow occurs frequently in switches due to the limited flow table storage space, which has seriously hampered thelarge-scale deployment of SDN. To mitigate this threat, we introduce a new, proactive switch space intelligent management framework that can react actively before table- overflow occurs. Our solution, referred to as CPD, contains three modules: flow table status collection, flow prediction and proactive flow entry deletion. To preserve the function of switch, flow prediction predicts the number of new flows entering the network based on historical information, and proactive flow entry deletion evaluates the likelihood of table-overflow according to the predicted value and the state of current flow table gathered by status collection and proactively deletes the flow entries through a flow-based eviction algorithm. Further, we determine the best sampling period by solving a multi-objective optimization problem. Finally, the simulation results show that CPD can prevent about 90% of table-overflow and significantly reduce over 20% occurrences of table-miss compared with existing mechanisms.

Moving Target Defense(MTD) provides a promising solution to reduce the chance of weakness exposure by constantly changing the target's attack surface. Though lots of MTD technologies have been researched to defend network attacks, there is little systematic study on security assessment of MTD. This paper proposes a novel method to quantify the security of MTD system which based on three factors: Vulnerability Entropy, Attack Entropy and Attenuation Entropy. This assessment model provides a theoretical and practical guidance for building MTD system and improving MTD technology.

SCADA (Supervisory Control and Data Acquisition) system is the core component of industrial and critical infrastructure, and cyber security of SCADA system has become the key consideration of system managers and engineers. Therefore, a great many of standards, guidelines and best practices have been developed to give reference of SCADA system cyber security, hoping to provide some instructions for system managers. Unfortunately, there is little consensus on what to do. Whats worse, it is difficult to choose the right one for a particular industrial scene. These standards are usually long and complex texts, whose reading and understanding often takes much time and effort. We provide a comprehensive and structured review of SCADA cyber security standards, guidelines and best practices with three dimensions: release time, geographic location and intended audience. Finally, we use the theory of defense-in-depth as a reference to evaluate these standards. It is concluded that no standard performs better than others on all the criteria and that we should integrate different standards to apply them to a specific industrial scene.

Third-party IME (Input Method Editor) apps are often the preference means of interaction for Android users' input. In this paper, we first discuss the insecurity of IME apps, including the Potentially Harmful Apps (PHA) and malicious IME apps, which may leak users' sensitive keystrokes. The current defense system, such as I-BOX, is vulnerable to the prefix-substitution attack and the colluding attack due to the post-IME nature. We provide a deeper understanding that all the designs with the post-IME nature are subject to the prefix-substitution and colluding attacks. To remedy the above post-IME system's flaws, we propose a new idea, pre-IME, which guarantees that "Is this touch event a sensitive keystroke?" analysis will always access user touch events prior to the execution of any IME app code. We designed an innovative TrustZone-based framework named IM-Visor which has the pre-IME nature. Specifically, IM-Visor creates the isolation environment named STIE as soon as a user intends to type on a soft keyboard, then the STIE intercepts, translates and analyzes the user's touch input. If the input is sensitive, the translation of keystrokes will be delivered to user apps through a trusted path. Otherwise, IM-Visor replays non-sensitive keystroke touch events for IME apps or replays non-keystroke touch events for other apps. A prototype of IM-Visor has been implemented and tested with several most popular IMEs. The experimental results show that IM-Visor has small runtime overheads.

In this paper, we design a game theoretical framework for improving the Quality of Service (QoS) in cooperative RAN caching. Considering the cooperation under both single cell transmission and joint transmission, the QoS metric is uniformly quantified as the total content delivery time. Although the formulated cooperative content placement problem is proved NP-hard, noticing the local cooperative characteristics, we transform the problem into Local Altruistic Gaming where the Nash Equilibrium (NE) can be guaranteed and distributive algorithms such as Spatial Adaptive Play (SAP) are applicable. Then, two distributed learning algorithms are proposed, where the former overcomes the execution difficulties over tremendous action set in traditional SAP, and the latter further accelerate the convergence by reducing the number of additional suboptimal NEs brought by the former. To further improve the computation efficiency, an updating scheme is constructed to enable parallel updating in the proposed algorithms. Finally, based on a real-world LTE traffic dataset, the performance of the proposed algorithms and the updating scheme have been validated.

Multi-path TCP has recently shown great potential to take advantage of the rich path diversity in data center networks (DCN) to increase transmission throughput. However, the small flows, which take a large fraction of data center traffic, will easily get a timeout when split onto multiple paths. Moreover, the dynamic congestions and node failures in DCN will exacerbate the reorder problem of parallel multi-path transmissions for large flows. In this paper, we propose DC2-MTCP (Data Center Coded Multi-path TCP), which employs a fast and light-weight coding method to address the above challenges while maintaining the benefit of parallel multi-path transmissions. To meet the high flow performance in DCN, we insert a very low ratio of coded packets with a careful selection of the packets to be coded. We further present a progressive decoding algorithm to decode the packets online with a low time complexity. Extensive ns2-based simulations show that with two orders of magnitude lower coding delay, DC2-MTCP can reduce on average 40% flow completion time for small flows and increase 30% flow throughput for large flows compared to the peer schemes in varying network conditions.

Cloud computing has become a promising paradigm in the field of Services Computing for its advantage of providing infrastructures and resources as a service. However, cloud networks consume huge amount of energy consumption due to the various applications and large scale of users with high mobility. In this paper, we investigate the problem of service migration to minimize the energy consumption of cloud infrastructures while ensuring the service delivery with satisfied latency and economic cost. We propose an energy-efficient migration scheme named SMPA considering the economic aspects and the quality of service. Furthermore, the mechanism of virtual machine consolidation running different services is also designed in SMPA, when the requests arrive, change or depart. Extensive simulations conducted on random topologies show that our proposal reduces requests' SLA violation ratio and improves the utilization of provider resources by service migration. Moreover, by taking advantage of physical resources, SMPA decreases the number of running hosts and reduces the power consumption while ensuring the operational cost effectively under dynamic workload scenarios.

With the increasing popularity of cloud computing, the huge amount of energy consumed by data centers has gained much attention. Current proposals address the energy efficiency problem by two major methods: optimizing the allocation of physical servers and network elements (routers or switches). In order to improve resource utilization and minimize the energy consumption, the former method focuses on virtual machine (VM) placement regardless of the inherent traffic between VMs. The latter designs power saving routing and flow scheduling while this method neglects the resource demands in VMs. In this paper, we jointly consider the VM placement and network routing to optimize energy cost. In addition, we take advantage of the centralized and global controller in Software Defined Networking (SDN) paradigm. Inspired by the idea of Data Field, we propose a novel algorithm to evaluate the importance and relationships among multiple VMs. The potential score based on Data Field is a more accurate global ranking considering the resource demands and inter-VM traffic. Extensive simulations are conducted on different scales of typical data center topologies, such as Fat-Tree and BCube. Results show that our proposal can reduce the number of active devices including the servers and network elements, and thereby saves power consumption. Moreover, the proposed algorithm improves network performance by decreasing the average hops of per flow.

This paper addresses mainly the problem of private data protection in network communication against eavesdropping attacks. As this kind of attacks is stealthy and untraceable, it is barely detectable for those feature detection or static configuration based passive defense approaches. We propose a Moving Target Defense(MTD) method by utilizing the protocol customization ability of Protocol-Oblivious Forwarding (POF). The novel full protocol stack randomization MTD can greatly increase the difficulty of implementing network eavesdropping attack and protect the privacy of the network communication process.

Video services are proliferating over today's mobile Internet and efforts have been made to improve their performance. The cross-layer video streaming that jointly optimizes the parameters at different protocol layers is a feasible solution but without bandwidth aggregation of multiple wireless networks. The cross-network video streaming can realize the bandwidth aggregation by using multiple overlapping wireless networks simultaneously. However, parameters at different protocol layers are optimized independently in the cross-network optimization. In this paper, we propose a joint cross-network and cross-layer optimized video streaming scheme that utilizes the bandwidth aggregation of cross-network video streaming and further improve the performance by jointly optimizing the parameters of different protocol layers in each network with a cross-layer manner. In the proposed scheme, the LTE and WCDMA networks are adopted. The bit-rate of the video at application layer, the rate allocation among networks and the parameters of physical layers in each network are jointly optimized. Experimental results show that the proposed scheme gains higher quality of experience in terms of PSNR than the state-of-the-art schemes.

Today, how to accurately predict the quality of experience (QoE) of the networking service is a very important issue for the network operator to optimize the service. However, due to the complex multi-dimensional characteristics of QoE, QoE estimation is extremely challenging. With utilizing the advantages of quality of service (QoS) in evaluating the networking performance, we exploit QoS/QoE correlation to predict QoE by building a QoSto-QoE mapping relationship. To fully consider the inter-dependency among QoS parameters towards forming the QoE, a Choquet integral based fuzzy measurement method is used to map QoS to QoE. Via extensive experiments in mobile VoD applications, the advancement and effectiveness of the proposed method are verified.

It is a challenge to improve utilization of physical resources when allocating resources for virtual data centers (VDCs). In this work we proposed two reliability-aware VDC embedding methods NMP and NMPD. To reduce embedding cost, the proposals try to split VMs into clusters based on topological potential and modularity and assign each cluster to a server. Via simulations, we show that NMP can accept more VDCs and help InPs improve the revenue. Although accepting a little less VDCs, NMPD can reduce resources occupied by VDCs and alleviate the congestion of core links.

The explosive growth of online videos brings a great pressure on LTE mobile networks caused by huge mobile data traffics. Deploying caches at the evolved packet core (EPC) and radio access network (RAN) in LTE mobile networks can efficiently relieve this pressure by the way of reducing duplicate content transmissions. In this paper, we propose collaborative caching algorithms for the LTE mobile network with caches deployed at the EPC and RAN to reduce the bandwidth cost of Internet access and improve the end-user experience. We decompose the caching problem into a content placement subproblem and a request routing subproblem. We solve the content placement subproblem with a greedy placement algorithm by utilizing its matroid and submodular properties. As for the request routing subproblem, we solve it by transforming it into the problem of maximizing a submodular function subject to a matroid constraint and present a greedy algorithm. Both the proposed algorithms can achieve at least 1=2 of the optimal solution. Experiment results show that our proposed algorithms can significantly improve the performance in terms of access cost and supported request compared with three reference algorithms.

Cloud computing is a promising paradigm for future computing platform. It enables the physical resources(computing, storage, networking, etc) to be provided on-demand. Despite the cloud computing brings many benefits to the IT network structure, it still faces new challenges for allocating heterogeneous resources automatically to services. Software Defined Networking (SDN) is a new concept of the network infrastructure as it decouples the control and data planes.With its characteristic of programmability, it's feasible to achieve network virtualization or create a slice of network in the form of virtual data centers(VDCs), which have pushed huge development of cloud computing. The VDCs embedding problem deals with allocating VDC requests to fulfill the requirements of cloud services with minimal cost and high revenue, which is an NPhard problem. In this paper, we propose an algorithm based on Entropy Weighted topological Potential considering multiple types of resources to tackle the problem in SDN-enabled data center network. Extensive simulations show that our proposed algorithm can embed more virtual requests efficiently with higher acceptance ratio and resource revenue over time.

TCP suffers from low throughput and high latency because of its expensive timeout based loss recovery mechanism in data center networks (DCNs). In this paper, we propose TCP with Adaptive Complementary Coding (TCP-ACC) to effectively address these problems. Without revising existing TCP congestion control, we first design a light-weight complementary coding scheme to avoid TCP timeout which will result in higher throughput and lower latency. In our scheme, the redundancy setting is adaptive to the real-time packet loss rate. Then we introduce Lyapunov optimization framework to find the optimal number of redundant coding packets for TCP-ACC, and we also prove that TCP-ACC can reduce the flow timeout probability close to that of the optimal complementary coding solution. Extensive NS2 simulations show that, compared with other three solutions for TCP's problems in DCNs, TCP-ACC can reduce the flow completion time by 45% and improve the flow throughput by 40% on average.

In this paper, we propose CGM-PS, a partial-decentralized, un-starving, work-conservative, and preemptive coflow scheduling scheme to shorten the Coflow Completion Time (CCT) for TCP flows in data center networks (DCNs). In CGMPS, we propose both inter- and intra- coflow scheduling policies. In inter-coflow scheduling, we present P-SEBF, which adopts a connected-graph model based novel concept Partialcoflow, to achieve approximate SEBF scheduling in a partial-decentralized manner. In intra-coflow scheduling, we present FP-MDFS to give flow-level priorities and appropriate rates to TCP flows for finishing the coflows as quick as possible without wasting network capacities in a decentralized manner. Trace-based simulation results show that, among existing coflow scheduling schemes, CGM-PS can achieve the minimal CCTs both on average and in the 90th percentile. In brief, CGM-PS only brings about similar scheduling overhead with the decentralized schemes, while it can achieve the CCT performance even better than the near optimal centralized scheme.

In energy-harvesting wireless sensor networks, sensor nodes equipped with a harvesting device scavenge the valuable energy from ambient environments. In this paper, we consider the routing problem of jointly considering the distance, the remaining energy and energy-harvesting capability of sensor nodes with the objective to route the collected data toward the sink node by going through the high-density harvesting energy areas in which sensor nodes are distributed with high density and with strong energy-harvesting capability. To address this, we first establish a “Hybrid Virtual Potential Field” and thereby design an efficient algorithm for deriving the harvesting energy balanced path for routing the network data along the high-density harvesting energy area. The simulation results show the effectiveness of our proposed algorithm on balancing the harvesting energy consumption by comparing with existing algorithms and by under different weather conditions.