Large language models(LLMs) are increasingly integrated with external systems through the Model Context Protocol(MCP),which standardizes tool invocation and has rapidly become a backbone for LLM-powered applications. While this paradigm enhances functionality,it also introduces a fundamental security shift:LLMs transition from passive information processors to autonomous orchestrators of task-oriented toolchains,expanding the attack surface,elevating adversarial goals from manipulating single outputs to hijacking entire execution flows. In this paper,we identify and characterize a systematic privacy-leakage attack pattern,termed Parasitic Toolchain Attacks,instantiated as MCP Unintended Privacy Disclosure(MCP-UPD). These attacks require no direct victim interaction;instead,adversaries embed malicious instructions into external data sources that LLMs access during legitimate tasks. Unlike traditional prompt injection and tool poisoning attacks,our attack targets the interconnected toolchain itself,assembling multiple legitimate tools into a coordinated workflow whose combined behavior accomplishes malicious objectives. In MCP-UPD,the malicious logic infiltrates the toolchain and unfolds in three phases:Parasitic Ingestion,Privacy Collection,and Privacy Disclosure,culminating in stealthy exfiltration of private data. Our root cause analysis reveals that MCP lacks both context-tool isolation and least-privilege enforcement,enabling adversarial instructions to propagate unchecked into sensitive tool invocations. To assess the severity,we design MCP-SEC and conduct the first large-scale security census of the MCP ecosystem,analyzing 12230 tools across 1360 servers. Our findings show that the MCP ecosystem is rife with real-world exploitable gadgets and diverse attack methods,underscoring systemic risks in MCP platforms and the urgent need for defense mechanisms in LLM-integrated environments.

The widespread adoption of encryption across web-based services is compelling both malicious attackers and network defenders to tailor their tool repositories to encrypted traffic. For various security applications in encrypted networks, the analysis of encrypted traffic lies as the fundamental basis. Due to the inherent concealment of content-related information in encrypted packets, the dynamics of encrypted traffic emerge as the discernible variable warranting comprehensive analysis. This paper explores inherent temporal correlations within the encrypted traffic and proposes a novel algorithm calledCriss-crossTrafficTransformer (CTT), tailored to address unique challenges in encrypted traffic analysis. CTT distinguishes itself by employing a specialized time series Transformer that innovatively utilizespatchingandcriss-cross attention module(CAM) to dissect and interpret encrypted traffic, with the “criss” part mining the long-/short-term temporal correlations across time, and the “cross” part capturing temporal correlations across multiple feature dimensions of encrypted traffic. CTT provides a unified framework capable of accommodating diverse analytical granularities, including packet-level, flow-level, and packet-to-flow level. Notably, CTT not only encompasses encrypted traffic classification but also extends to encrypted traffic forecasting, an area that remains largely underexplored in existing literature. We evaluate CTT in the context of fingerprinting attacks and malware detection over 5 real-world datasets against 13 benchmarks. The results indicate that CTT achieves up to 15.56% performance improvement over SOTA solutions for encrypted traffic classification. Particularly, CTT demonstrates over 92.5% forecasting accuracy, which is comparable to SOTA performances in the seen-and-classify scenario, suggesting its potential applicability to broader domains like social network behavioral analysis. Our code is available athttps://github.com/Amanda-HuaDing/Criss-cross_Traffic_Transformer.

Large language models (LLMs) have demonstrated exceptional performance across a wide variety of domains. Nonetheless, generalist LLMs continue to fall short in reasoning tasks necessitating specialized knowledge, e.g., emotional sociology and medicine. Prior investigations into specialized LLMs focused on domain-specific training, which entails substantial efforts in domain data acquisition and model parameter fine-tuning. To address these challenges, this paper proposes the Way-to-Specialist (WTS) framework, which synergizes retrieval-augmented generation with knowledge graphs (KGs) to enhance the specialized capability of LLMs in the absence of specialized training. In distinction to existing paradigms that merely utilize external knowledge from general KGs or static domain KGs to prompt LLM for enhanced domain-specific reasoning, WTS proposes an innovative ''LLM↻KG'' paradigm, which achieves bidirectional enhancement between specialized LLM and domain knowledge graph (DKG). The proposed paradigm encompasses two closely coupled components: the DKG-Augmented LLM and the LLM-Assisted DKG Evolution. The former retrieves question-relevant domain knowledge from DKG and uses it to prompt LLM to enhance the reasoning capability for domain-specific tasks; the latter leverages LLM to generate new domain knowledge from processed tasks and use it to evolve DKG. WTS closes the loop between DKG-Augmented LLM and LLM-Assisted DKG Evolution, enabling continuous improvement in the domain specialization as it progressively answers and learns from domain-specific questions. We validate the performance of WTS on 7 datasets (e.g., TweetQA, ChatDoctor5k) spanning 6 domains, e.g., emotional sociology, medical, ect. The experimental results show that WTS surpasses the previous SOTA in 5 specialized domains, and achieves a maximum performance improvement of 11.3%.

With the increasing size of Internet of Things (IoT) devices, cyber threats to IoT systems have increased. Federated learning (FL) has been implemented in an anomaly-based intrusion detection system (NIDS) to detect malicious traffic in IoT devices and counter the threat. However, current FL-based NIDS mainly focuses on global model performance and lacks personalized performance improvement for local data. To address this issue, we propose a novel personalized federated meta-learning intrusion detection approach (PerFLID), which allows multiple participants to personalize their local detection models for local adaptation. PerFLID shifts the goal of the personalized detection task to training a local model suitable for the client’s specific data, rather than a global model. To meet the real-time requirements of NIDS, PerFLID further refines the client selection strategy by clustering the local gradient similarities to find the nodes that contribute the most to the global model per global round. PerFLID can select the nodes that accelerate the convergence of the model, and we theoretically analyze the improvement in the convergence speed of this strategy over the personalized federated learning algorithm. We experimentally evaluate six existing FL-NIDS approaches on three real network traffic datasets and show that our PerFLID approach outperforms all baselines in detecting local adaptation accuracy by 10.11% over the state-of-the-art scheme, accelerating the convergence speed under various parameter combinations.

In the real world, the stable operation of a network is usually inseparable from the mutual support of other networks. In such an interdependent network, a node in one layer may depend on multiple nodes in another layer, forming a complex one-to-many dependence relationship. Meanwhile, there may also be higher-order interactions between multiple nodes within a layer, which increase the connectivity within the layer. Interlayer dependencies and intralayer connectivity may become key factors affecting network reliability, because failures within a layer will propagate to another layer through dependencies, and the cascading effects within and between layers may trigger catastrophic network collapse. However, existing research on one-to-many interdependence often neglects intralayer higher-order structures and lacks a unified theoretical framework for interlayer dependencies. Moreover, current research on interdependent higher-order networks typically assumes idealized one-to-one interlayer dependencies, which does not reflect the complexity of real-world systems. These limitations hinder a comprehensive understanding of how such networks withstand failures. Therefore, this article investigates the robustness of one-to-many interdependent higher-order networks under random attacks. Depending on whether node survival requires at least one dependence edge or multiple dependence edges, we propose four interlayer interdependence conditions and analyze the network’s robustness after cascading failures induced by random attacks. Using percolation theory, we establish a unified theoretical framework that reveals how higher-order interaction structures within intralayers and interlayer coupling parameters affect network reliability and system resilience. In addition, we extend our study to partially interdependent hypergraphs. We validate our theoretical analysis on both synthetic and real-data-based interdependent hypergraphs, offering insights into the optimization of network design for enhanced reliability.

This paper proposes Meta Parallel Graph Neural Network (MPGNN) to establish a scalable Network Intrusion Detection System (NIDS) for large-scale Internet of Things (IoT) networks. MPGNN leverages a meta-learning framework to optimize the parallelism of GNN-based NIDS. The core of MPGNN is a coalition formation policy that generates meta-knowledge for partitioning a massive graph into multiple coalitions/subgraphs in a way that maximizes the performance and efficiency of parallel coalitional NIDSs. We propose an offline reinforcement learning algorithm, called Graph-Embedded Adversarially Trained Actor-Critic (G-ATAC), to learn a coalition formation policy that jointly optimizes intrusion detection accuracy, communication overheads, and computational complexities of coalitional NIDSs. In particular, G-ATAC learns to capture the temporal dependencies of network states and coalition formation decisions over offline data, eliminating the need for expensive online interactions with large IoT networks. Given generated coalitions, MPGNN employs E-GraphSAGE to establish coalitional NIDSs which then collaborate via ensemble prediction to accomplish intrusion detection for the entire network. We evaluate MPGNN on two real-world datasets. The experimental results demonstrate the superiority of our method with substantial improvements in F1 score, surpassing the state-of-the-art methods by 0.38 and 0.29 for the respective datasets. Compared to the centralized NIDS, MPGNN reduces the training time of NIDS by 41.63% and 22.11%, while maintaining an intrusion detection performance comparable to centralized NIDS.

Artificial intelligence (AI)-based cybersecurity services offer significant promise in many scenarios, including malware detection, content supervision, and so on. Meanwhile, many commercial and government applications have raised the need for intellectual property protection of using deep neural network (DNN). Existing studies (e.g., watermarking techniques) on intellectual property protection only aim at inserting secret information into DNNs, allowing producers to detect whether the given DNN infringes on their own copyrights. However, since the availability protection of learning models is rarely considered, the piracy model can still work with high accuracy. In this paper, a novel model locking (M-LOCK) scheme for the DNN is proposed to enhance its availability protection, where the DNN produces poor accuracy if a specific token is absent, while it maps only the tokenized inputs into correct predictions. The proposed scheme performs the verification process during the DNN inference operation, actively protecting models' intellectual property copyright at each query. Specifically, to train the token-sensitive decision-making boundaries of DNNs, a data poisoning-based model manipulation (DPMM) method is also proposed, which minimizes the correlation between the dummy outputs and correct predictions. Extensive experiments demonstrate the proposed scheme could achieve high reliability and effectiveness across various benchmark datasets as well as typical model protection methods.

Anti-malware engines report malware labels to detail malice, typically including tags of family, behavior, and platform classes. This capability has been heavily used by the security community to annotate malware families and build reference datasets, which is referred to as crowdsourcing malware family annotation. However, how to associate tags with their corresponding classes in chaotic malware labels (extract class-determined tags) and how to infer ground truth for weakly-tagged samples that hold controversial tags remain open problems. In this paper, we present a novel annotation pipeline to advance further, which includes an incremental parsing scheme and a maximum likelihood estimation scheme. The incremental parsing scheme treats behavior and platform tags as locators and achieves incremental parsing by introducing and iterating the following two algorithms: location first search, which hits family tags using locators, and co-occurrence first search, which finds new locators by family tags. The maximum likelihood estimating scheme models an engine’s ability to identify different families as a confusion matrix and introduces an expectation-maximization algorithm to estimate the matrix, as well as the unknown truth of samples. Experiments across four benchmark datasets indicate that our pipeline outperforms existing work, improving label-level parsing accuracy by an average of 29%, and improving inferring accuracy on weakly-tagged samples by an average of 9%. Our pipeline decouples parsing and inferring, which would pave the way for research on crowdsourcing malware family annotation.

Backdoor attacks have emerged as an urgent threat to Deep Neural Networks (DNNs), where victim DNNs are furtively implanted with malicious neurons that could be triggered by the adversary. To defend against backdoor attacks, many works establish a staged pipeline to remove backdoors from victim DNNs: inspecting, locating, and erasing. However, in a scenario where a few clean data can be accessible, such pipeline is fragile and cannot erase backdoors completely without sacrificing model accuracy. To address this issue, in this paper, we propose a novel data-free holistic backdoor erasing (DHBE) framework. Instead of the staged pipeline, the DHBE treats the backdoor erasing task as a unified adversarial procedure, which seeks equilibrium between two different competing processes: distillation and backdoor regularization. In distillation, the backdoored DNN is distilled into a proxy model, transferring its knowledge about clean data, yet backdoors are simultaneously transferred. In backdoor regularization, the proxy model is holistically regularized to prevent from infecting any possible backdoor transferred from distillation. These two processes jointly proceed with data-free adversarial optimization until a clean, high-accuracy proxy model is obtained. With the novel adversarial design, our framework demonstrates its superiority in three aspects: 1) minimal detriment to model accuracy, 2) high tolerance for hyperparameters, and 3) no demand for clean data. Extensive experiments on various backdoor attacks and datasets are performed to verify the effectiveness of the proposed framework. Code is available at https://github.com/yanzhicong/DHBE

VirusTotal is widely used for malware annotation by providing malware labels from a large set of anti-malware engines. A long-standing challenge in using these inconsistent labels is extracting class-determined tags. In this paper, we present Tagclass,a tool based on incremental parsing to associate tags with their corresponding family, behavior, and platform classes. Tagclasstreats behavior and platform tags as locators and achieves incremental parsing by introducing and iterating the following two algorithms: 1) location first search, which hits family tags using locators, and 2) co-occurrence first search, which finds new locators by family tags. Experiments across two benchmark datasets indicate Tagclassoutperforms existing methods, improving the parsing accuracy by 21% and 28%, respectively. To the best of our knowledge, Tagclassis the first tag class-determined malware label parsing tool, which would pave the way for research on crowdsourcing malware annotation. Tagclasshas been released to the community11https://github.com/crowdma/tagclass.

Software-defined industrial Internet of things (SD-IIoT) exploits federated learning to process the sensitive data at edges, while adaptive poisoning attacks threat the security of SD-IIoT. To address this problem, this article proposes a multi-tentacle federated learning (MTFL) framework, which is essential to guarantee the trustness of training data in SD-IIoT. In MTFL, participants with similar learning tasks are assigned to the same tentacle group. To identify adaptive poisoning attacks, a tentacle distribution-based efficient poisoning attack detection (TD-EPAD) algorithm is presented. And also, to minimize the impact of adaptive poisoning data, a stochastic tentacle data exchanging (STDE) protocol is also proposed. Simultaneously, to protect the tentacle’s privacy in STDE, all exchanged data will be processed by differential privacy technology. A MTFL prototype system is implemented, which provides extensive ablation experiments and comparison experiments, demonstrating that the accuracy of the global model under attack scenario can be improved with 40%.

Temporal graphs are ubiquitous data structures in many scenarios, including social networks, user-item interaction networks, etc. In this paper, we focus on predicting the exact time of future interactions between node pairs on a temporal graph. This problem can support interesting applications including time-sensitive items recommendation, congestion prediction on road networks, etc. We present the Graph Neural Point Process (GNPP) to tackle this problem. GNPP relies on the graph neural message passing and the temporal point process framework. Most previous graph neural models devised for temporal graphs either utilize the chronological order information or rely on specific point process models, ignoring the exact timestamps and complicated temporal patterns. In GNPP, we adapt a time encoding scheme to map real-valued timestamps to a high-dimensional vector space so that the temporal information can be modeled precisely. Further, GNPP considers the structural information of graphs by conducting message passing aggregation on the constructed line graph. The obtained representation defines a neural conditional intensity function that models events’ generation mechanisms for predicting interactions’ time between node pairs. We evaluate this model on several synthetic and real-world temporal graphs where it outperforms recently proposed neural point process models and graph neural models devised for temporal graphs. We further conduct ablation comparisons and visual analyses to shed some light on the learned model and understand the functionality of important components comprehensively.

With the empirical success of Graph Neural Networks (GNNs) on graph-related tasks, it is intriguing to investigate their theoretical power on these tasks. In this paper, we focus on GNNs’ theoretical power on substructure counting, a fundamental yet challenging task in many applications. Previous works have proven that the 2-dimensional Weisfeiler-Leman algorithm (2-WL) equivalent GNNs can only count limited substructures. However, the substructure counting ability of theoretically more powerful and computationally tractable GNNs remains unclear. In this paper, we study conditions for substructures to be theoretically countable by k-WL equivalent GNNs, and then focus on 3-WL equivalent ones, which are currently the most theoretically powerful instances with practical computational cost. Further, we propose an algorithm to determine the countability of substructures for 3-WL equivalent GNNs. Our results reveal that 3-WL equivalent GNNs can count considerably more substructures than 2-WL equivalent ones. However, the proportion of countable patterns and prediction performance decrease as the pattern size increases. Therefore, we propose a Layer Permutation Pooling (LPP) model for better substructure counting performance. LPP first decomposes the data graph into subgraphs. Then we propose a layer permutation scheme to represent each decomposed subgraph as a set of matrices. Finally, LPP utilizes a neural network to conduct predictions on matrices. We compare LPP with several state-of-the-art GNNs on various datasets. Experimental results show that LPP outperforms baselines by 84% on average with the RMSE metric.

In many route planning applications, finding constrained shortest paths (CSP) is an important and fundamental problem. CSP aims to find the shortest path between two nodes on a graph while satisfying a path constraint. Solving CSPs requires a large search space and is prohibitively slow on large graphs, even with the state-of-the-art parallel solution on GPUs. The reason lies in the lack of effective navigational information and pruning strategies in the search procedure. In this paper, we propose SPEC, a Shortest Path Enhanced approach for solving the exact CSP problem. Our design rationales of SPEC rely on the observation that the shortest path (SP) provides valuable information in the search procedure of CSP. Hence, we propose a label priority that distinguishes promising candidate paths based on SP. We further devise efficient pruning and teleporting strategies utilizing SP lengths and costs, which eliminates unfeasible paths at an early stage. Furthermore, we observe that the expansion number at each search iteration affects the overall performance significantly. Thus, we devise an adaptive controller based on reinforcement learning. We also show that SPEC works seamlessly with the parallel implementation. Extensive experimental results on 8 read-world graphs reveal that single thread SPEC achieves an order of magnitude speedup over the state-of-the-art GPU-based method. The parallel implementation boosts SPEC 3 to 5 times further.

The threat of data-poisoning backdoor attacks on learning algorithms typically comes from the labeled data. However, in deep semi-supervised learning (SSL), unknown threats mainly stem from the unlabeled data. In this paper, we propose a novel deep hidden backdoor (DeHiB) attack scheme for SSL-based systems. In contrast to the conventional attacking methods, the DeHiB can inject malicious unlabeled training data to the semi-supervised learner so as to enable the SSL model to output premeditated results. In particular, a robust adversarial perturbation generator regularized by a unified objective function is proposed to generate poisoned data. To alleviate the negative impact of the trigger patterns on model accuracy and improve the attack success rate, a novel contrastive data poisoning strategy is designed. Using the proposed data poisoning scheme, one can implant the backdoor into the SSL model using the raw data without hand-crafted labels. Extensive experiments based on CIFAR10 and CIFAR100 datasets demonstrated the effectiveness and crypticity of the proposed scheme.

Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets appear in sequential orders. And the orders may lead to interesting applications. While a binary link prediction formulation fails to handle such an order-sensitive case. In this paper, we focus on such an interaction order prediction problem among a given node set on temporal graphs. For the technical aspect, we develop a graph neural network model named Temporal ATtention network (TAT), which utilizes the fine-grained time information on temporal graphs by encoding continuous real-valued timestamps as vectors. For each transformation layer of the model, we devise an attention mechanism to aggregate neighborhoods' information based on their representations and time encodings attached to their specific edges. We also propose a novel training scheme to address the permutation-sensitive property of the problem. Experiments on several real-world temporal graphs reveal that TAT outperforms some state-of-the-art graph neural networks by 55% on average under the AUC metric.

Influence diffusion estimation is a crucial problem in social network analysis. Most prior works mainly focus on predicting the total influence spread, i.e., the expected number of influenced nodes given an initial set of active nodes (aka. seeds). However, accurate estimation of susceptibility, i.e., the probability of being influenced for each individual, is more appealing and valuable in real-world applications. Previous methods generally adopt Monte Carlo simulation or heuristic rules to estimate the influence, resulting in high computational cost or unsatisfactory estimation error when these methods are used to estimate susceptibility. In this work, we propose to leverage graph neural networks (GNNs) for predicting susceptibility. As GNNs aggregate multi-hop neighbor information and could generate over-smoothed representations, the prediction quality for susceptibility is undesirable. To address the shortcomings of GNNs for susceptibility estimation, we propose a novel DeepIS model with a two-step approach: (1) a coarse-grained step where we estimate each node's susceptibility coarsely; (2) a fine-grained step where we aggregate neighbors' coarse-grained susceptibility estimations to compute the fine-grained estimate for each node. The two modules are trained in an end-to-end manner. We conduct extensive experiments and show that on average DeepIS achieves five times smaller estimation error than state-of-the-art GNN approaches and two magnitudes faster than Monte Carlo simulation.

The next-generation network (6G) has more strict requirements for the online learning ability and high interpretability of the learned systems. Machine learning is expected to be essential to assist in making the networks efficient and adaptable, but most promising methods often are treated as “black boxes” due to the deep structures and high nonlinearity. Therefore, this article attempts to study the interpretations of machine learning algorithms to make them more applicable to the 6G-enabled Internet of things (IoT) networks. Typically, this article focuses on the new model GBDT2NN, which distills the knowledge learned by gradient boosting decision tree (GBDT) into neural network (NN) models to retain the learning ability of numerical data and rise the ability of online learning at the same time, but it loses the interpretability. This article conducts an empirical study on explaining individual prediction of GBDT2NN by taking use of the feature importance learned from GBDT, and then further explores whether the explanation can improve the approximation process. In addition, this article proposes two methods to obtain the interpretations: 1) the independent method and 2) the joint method. The experiments on several data sets of IoT networks show that the proposed methods can achieve better performance on both explanations and predictions.

Semi-Supervised Learning (SSL) is a powerful derivative for humans to discover the hidden knowledge, and will be a great substitute for data taggers. Although the availability of unlabeled data rises up a huge passion to SSL, the untrustness of unlabeled data leads to many unknown security risks. In this paper, we first identify an insidious backdoor threat of SSL where unlabeled training data are poisoned by backdoor methods migrated from supervised settings. Then, to further exploit this threat, a Deep Neural Backdoor (DeNeB) scheme is proposed, which requires less data poisoning budgets and produces stronger backdoor effectiveness. By poisoning a fraction of unlabeled training data, the DeNeB achieves the illegal manipulation on the trained model without modifying the training process. Finally, an efficient detection-and-purification defense (DePuD) framework is proposed to thwart the proposed scheme. In DePuD, we construct a deep detector to locate trigger patterns in the unlabeled training data, and perform secured SSL training with purified unlabeled data where the detected trigger patterns are obfuscated. Extensive experiments based on benchmark datasets are performed to demonstrate the huge threatening of DeNeB and the effectiveness of DePuD. To our best knowledge, this is the first work to achieve the backdoor and its defense in semi-supervised learning.

The learning automaton (LA) that simulates the interaction between an intelligent agent and a stochastic environment to learn the optimal action is an important tool in reinforcement learning. Being confronted with an unknown environment, most learning automata have more than one parameters to be tuned during a pretraining process in which the LA interacts with the environment. Only after the parameters are tuned properly, an LA can act most properly during the training procedure to obtain the optimal behavior. The cost of parameter tuning can be enormous, e.g., possibly millions of interactions are required to seek the best parameter configuration. Therefore, the parameter-free LA that uses identical parameters for every environment and saves further tuning has become the hot spot of this research. This article proposes an efficient parameter-free learning automaton (EPFLA) that depends on a separating function (SF). Taking advantage of both frequentist inference and Bayesian inference, the SF plays a dual role in the proposed scheme: 1) evaluating the difference in performance between actions in the environment and 2) exploring actions by coining an action selection strategy. A proof is provided to ensure the ϵ -optimality of EPFLA. Comprehensive comparisons verify the privileges of EPFLA over both parameter-based schemes and existing parameter-free schemes.

The problem of maximizing the spread of influence by selecting a subset of participants in a social network as sources, known as influence maximization, is a fruitful topic with straightforward application value. Greedy algorithms that select the optimal node one by one lay the foundation of follow- up research, and plentiful studies have been taken to improve the efficiency of greedy-based algorithms. However, the greedy methods can easily fall into adversary pitfalls, and corresponding improvements have been few. In this paper, a conjugate learning automata based method, utilizing the ability of cooperation in learning automata games, is proposed to obtain better- than-greedy propagation range. Comprehensive simulations in both synthetic and real-world datasets verify that the proposed method can attain better propagation range in some scenarios and is equally competitive respecting efficiency.

The machine-to-machine (M2M) communications, which achieve the implementation of Internet of Things (IoT), can be carried over wireless cellular networks. The massive random access (RA) in M2M communications will cause radio access network congestion in the base station (BS), leading to sharp deterioration in access delay and access probability. Access class barring (ACB) that can directly control the flow of machine-type communication (MTC) devices by an ACB factor is an efficient scheme to prevent the BS from traffic overload. In wireless cellular networks, the RA resources (i.e., preambles) are shared by M2M and human-to-human (H2H) devices, and research on ACB scheme ordinarily assumes that a restricted number of preambles are assigned to M2M traffic. However, when suffering from massive access in M2M communications, it is desirable to rapidly satisfy the access requests from MTC devices using all available preambles, especially in time-sensitive IoT scenarios. In this paper, we study the massive access problem in M2M traffic centered scenarios where M2M and H2H traffic can apply for all available preambles without distinction. Utilizing the self-adaptive learning property of learning automata, we further propose a novel learning automata-based ACB (LA-ACB) scheme. Simulation results show that the LA-ACB scheme achieves the performance close to theoretical optimality. The BS equipped with the LA-ACB scheme can effectively control the M2M traffic by dynamically adjusting the ACB factor under the interference of H2H traffic and provide quality services for both M2M and H2H traffic.

Learning automata (LA), which intellectually explores its optimal state by interacting with an external environment continuously, is encountered widely in artificial intelligence. In the evaluation of LA, it has always been a key issue how to tradeoff between "accuracy" and "speed," which substantially touches on parameter tuning. A latest issue in the design of LA methodology involves bearing a parameter-free property, thus removing the tremendous expenses brought by parameter tuning. Nevertheless, the currently existing parameter-free LA schemes generally maintain a Monte-Carlo technique, which helps avoid the tuning process at the cost of more computations. This paper examines a new measurement of parameter-free LA schemes based on statistics which overcome the difficulties found in other counterparts. Specifically, it has innovatively disengaged from the dependance on Monte-Carlo methods. Of greater significance, the learning mechanisms operating in the common stationary environments are likewise extended to the nonstationary environments. Simulations confirm the effectiveness and efficiency of the proposed algorithm, especially its low computation consumption as well as the strong tracking capability to abrupt environmental changes.

Deep neural network are one of the most powerful model for machine learning, which can learn the underlying patterns automatically from a large amount of data. So it can be extensively used in more and more Internet-of-Things (IoT) applications. However, the training of deep models is difficult, suffering from overfitting and gradient vanishing problem. Besides, the large amount of parameters and multiplication operations make it impractical for most deep learning models to directly execute on target hardware. In this paper, we propose a method of gradually pruning the weakly connected weights to improve the traditional stochastic gradient descent. And we adopt a reinforcement learning method called learning automata to find the weakly connected weights on account of its strong policy-making ability in stochastic and nonstationary environment. Our proposed method can learn a more effective and sparsely connected architecture during training from the initially fully connected neural networks. The experiments on MNIST show that our method have stronger power to defeat overfitting and can get better generalization performance on test set. Meanwhile, the thin and sparsely connected model we get can be more suitable for IoT applications.

This paper considers the stochastic point location (SPL) problem as a learning mechanism trying to locate a point on a real line via interacting with a random environment. Compared to the stochastic environment in the literatures that confines the learning mechanism to moving in two directions, i.e., left or right, this paper introduces a general triple level stochastic environment which not only tells the learning mechanism to go left or right, but also informs it to stay unmoved. It is easy to understand, as we will prove in this paper, that the environment reported in the previous literatures is just a special case of the triple level environment. And a new learning algorithm, named as random walk-based triple level learning algorithm, is proposed to locate an unknown point under this new type of environment. In order to examine the performance of this algorithm, we divided the triple level SPL problems into four distinguished scenarios by the properties of the unknown point and the stochastic environment, and proved that even under the triple level nonstationary environment and the convergence condition having not being satisfied for some time, which are rarely considered in existing SPL problems, the proposed learning algorithm is still working properly whenever the unknown point is static or evolving with time. Extensive experiments validate our theoretical analyses and demonstrate that the proposed learning algorithms are quite effective and efficient.

Conventional spectrum refarming (SR) techniques assemble the legacy services to partial licensed spectrum, and free up the remained spectrum for operating other communication systems. In this paper, we propose a new broadband SR framework in which the orthogonal-frequency division multiple access (OFDMA) system dynamically shares the code division multiple access (CDMA) spectrum, which contains multiple bands in a concurrent manner. The interference margin provided by the downlink isometric random precoded CDMA system is first derived. To protect all the CDMA users, interference constraints that regulate the OFDMA transmission are then formulated. We formulate the joint CDMA load planning and OFDMA resource allocation problem for the SR system. By applying primal decomposition, it is shown that the higher-level problem is non-convex in general. We first propose an efficient algorithm to find the myopic optimal solution by investigating the derivative property of the higher-level problem. Through enhancing the original constrains, the higher-level problem is shown to be convex and solved with another efficient algorithm. Simulation results are provided to evaluate the SR performance, illustrating the significance of the CDMA load planning on the OFDMA throughput, the advantage of the proposed SR model over conventional SR, and the protection to the CDMA system.

Spectrum sensing based dynamic spectrum sharing is one of the key innovative techniques in future 5G communications. When realistic mobile scenarios are concerned, the location of primary user (PU) is of great significance to reliable spectrum detections and cognitive network enhancements. Given the dynamic disappearance of its emission signals, the passive locations tracking of PU, nevertheless, remains dramatically different from existing positioning problems. In this investigation, a new joint estimation paradigm, namely deep sensing, is proposed for such challenging spectrum and location awareness applications. A major advantage of this new sensing scheme is that the mutual interruption between the two unknown quantities is fully considered and, therefore, the PU's emission state is identified by estimating its moving positions jointly. Taking both PU's unknown states and its evolving positions into account, a unified mathematical model is formulated relying on a dynamic state-space approach. To implement the new sensing framework, a random finite set (RFS) based Bernoulli filtering algorithm is then suggested to recursively estimate unknown PU states accompanying its time-varying locations. Meanwhile, the sequential importance sampling is used to approximate intractable posterior densities numerically. Furthermore, an adaptive horizon expanding mechanism is specially designed to avoid the mis-tracking aroused by the intermittent disappearance of PU. Experimental simulations demonstrate that, even with mobile PUs, spectrum sensing can be realized effectively by tracking its locations incessantly. The location information, as an extra gift, may be utilized by cognitive performance optimizations.

Abstract Network coding has emerged some exciting future because of its smart technology in wireless sensor networks. At the same time, it is facing security attacks, especially conspiracy Attack. Most existing security strategies are concentrated on coding design, there has been almost no consideration from topological structure. In this background, a weakly‐secure scheme is proposed from the perspective of topology. Considering the performance of this scheme, an advanced scheme is put forward later. Simulations show that the two strategies can prevent cooperative eavesdroppers from acquiring any useful information transmitted from source node to sink node and the performance of advanced scheme is better. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract The wide use of high‐performance image acquisition devices and powerful image‐processing software has made it easy to tamper images for malicious purposes. Image splicing, which has constituted a menace to integrity and authenticity of images, is a very common and simple trick in image tampering. Therefore, image‐splicing detection is of great importance in digital forensics. In this paper, an effective framework for revealing image‐splicing forgery is proposed. First, the local binary pattern operator is used to model magnitude components of two‐dimensional arrays obtained by applying multisize block discrete cosine transform to test images. Then, all of bins of histograms computed from local binary pattern codes are served as discriminative features for image‐splicing detection. After that, kernel principal component analysis is utilized to reduce the dimensionality of the proposed features to avoid the high computational complexity, high mutual correlation among the constructed features and possible overfitting for support vector machine classifier. Finally, support vector machine classifier is employed to distinguish spliced images from authentic images by using the final dimensionality‐reduced feature set. The experiment results show that the proposed method can perform better than some state‐of‐the‐art methods in terms of the detection performance over the Columbia image‐splicing detection evaluation dataset. Copyright © 2013 John Wiley & Sons, Ltd.

In this paper, spectrum sensing is investigated and a new detection framework, namely, deep sensing (DS), is proposed for more challenging scenarios of future dynamic spectrum sharing. In contrast to existing methods, the DS scheme is designed to proactively recover and exploit some other informative states associated with realistic cognitive links (e.g., fading gains), except detecting the occupancy of primary-band. A unified mathematical model, relying on the dynamic state-space approach, is formulated, in which the Bernoulli random finite set (RFS) is further exploited to theoretically characterize complex DS procedures. A Bernoulli filter algorithm is suggested to recursively estimate unknown PU states accompanying related link information, which is implemented by particle filtering based on numerical approximations. The proposed DS algorithm is applied to detect primary users under time-varying fading channel, which may increase the observation uncertainty and, therefore, deteriorate the sensing performance. With this new framework, the time-varying fading gain, modeled as a stochastic discrete-state Markov chain (DSMC), is estimated along with unknown PU states. Simulations demonstrate that, by exploiting the underlying dynamic fading property, the sensing performance will surpass other traditional schemes. The DS scheme may be conveniently generalized to other applications, which will promote sensing performance and provides a new paradigm for next-generation spectrum sharing.

In this paper, a 2-D noncausal Markov model is proposed for passive digital image-splicing detection. Different from the traditional Markov model, the proposed approach models an image as a 2-D noncausal signal and captures the underlying dependencies between the current node and its neighbors. The model parameters are treated as the discriminative features to differentiate the spliced images from the natural ones. We apply the model in the block discrete cosine transformation domain and the discrete Meyer wavelet transform domain, and the cross-domain features are treated as the final discriminative features for classification. The support vector machine which is the most popular classifier used in the image-splicing detection is exploited in our paper for classification. To evaluate the performance of the proposed method, all the experiments are conducted on public image-splicing detection evaluation data sets, and the experimental results have shown that the proposed approach outperforms some state-of-the-art methods.

With the development of image tampering detection, more and more features are involved to improve the detection rate, and nowadays the high-dimensional features based methods get the state-of-the-art detection accuracies. However, the high dimensionality will cause excessive time cost in the classification phase, moreover it would probably introduce redundant features which will confuse the classifier. An effective scheme based on Distributed Local Margin Learning (D-LML) is proposed in this paper to solve the problems caused by the high-dimensionality of features in the image tampering detection work. Local Margin Learning algorithm distributed to different clients is employed to rank the importance of the original features, and we can get features with low dimensionality by preserving the important features while excluding the insignificant features. Experimental results show that the D-LML method could greatly reduce the dimensionality of the original features, and keep the detection rates fluctuating in a relatively small range.

Recently, detecting the traces introduced by the content-preserving image manipulations has received a great deal of attention from forensic analyzers. It is well known that the median filter is a widely used nonlinear denoising operator. Therefore, the detection of median filtering is of important realistic significance in image forensics. In this letter, a novel local texture operator, named the second-order local ternary pattern (LTP), is proposed for median filtering detection. The proposed local texture operator encodes the local derivative direction variations by using a 3-valued coding function and is capable of effectively capturing the changes of local texture caused by median filtering. In addition, kernel principal component analysis (KPCA) is exploited to reduce the dimensionality of the proposed feature set, making the computational cost manageable. The experiment results have shown that the proposed scheme performs better than several state-of-the-art approaches investigated.

Cognitive radio is a promising technology for sharing the underutilized frequency bands that have been licensed to primary users. However, due to the uncertainty in detecting the existence of the primary user, the secondary user may interfere with the primary users when both primary and secondary users are active simultaneously. Therefore, understanding the interference and its consequences on the cognitive network is critical. Unlike the statistical models previously reported in the literature that aim at approximation of the interference, based on the solid mathematical analysis, we propose an accurate model for describing the co-channel interference with probability density function, cumulative distribution function, mean, and variance of the interference suffered by the primary users. The proposed model not only takes into account a number of factors, such as the spectrum-sensing scheme, the spatial distribution of secondary users, and the channel conditions, including shadowing and Nakagami fading, but also gives an exact mathematical expression of the influences from these factors. The developed framework supports practical applications such as evaluating the cognitive network of any spatial shape and density of the secondary users and the methods of power control and spectrum sensing used by the secondary users. Simulation results are provided to verify the effectiveness of the analytical model.

The performance of error concealment (EC) for damaged intra-frames (or I-frames) is very important for real time video transmission via error-prone network. Conventional algorithms essentially exploit either copying or interpolation from spatial neighbors and suffer from poor visual quality. This paper proposes an intra-frame EC adaptive algorithm framework (I-ECAF) which gives priority to temporal EC as the first, spatial copying as the second and spatial interpolation as the last. I-ECAF evaluates their feasibility by measuring the temporal or spatial similarity per a recent image quality metric, i.e., the weighted peak signal-to-noise ratio (WPSNR). Demonstrated by extensive experiments, the proposed I-ECAF gains attractive concealment accuracy, an increase from 0.06dB to 1.14dB of PSNR in comparison with the algorithm embedded within JM18.0.

In this paper, a noncausal Markov model is proposed for digital image splicing detection. Different from the traditional Markov model in image splicing detection, the proposed approach models an observation array as a 2-D noncausal signal and captures the underlying statistical characteristics. We give the solutions to the model and the model parameters are treated as discriminative features for classification (detection). To evaluate the generalization and effectiveness of the proposed method, we apply the model in the block DCT domain and discrete Meyer wavelet transform domain respectively and experimental results have shown that the proposed approach outperforms most of the state-of-the-art methods.

The pixel-based contour map is one of the most common used shape representation methods for shape matching in object recognition field. However it is difficult to remain accurate and efficient at the same time when recognizing the objects with diversity of postures or different presence from different perspectives. To solve this problem, in this paper we propose an angle-based shape matching approach by introducing a new concept of angle-based features. Furthermore, the object recognition process adopting such angle-based shape matching approach is described in detail. With numerous experiments conducted on the Weizmann Horse dataset, we demonstrate that the proposed method is accurate, efficient and robust towards different poses and resolutions at the same time.

We propose a neural network based approach for call admission control (CAC), which is applicable to very general traffic. In our approach, a feedforward neural network is used to predict whether a new call can be accepted. The input vector of the neural network consists of a set of data reflecting the first and second-order statistical properties of the input aggregate stream, and its dimension is independent of the number of traffic classes. In addition, we give a novel ant algorithm to train the neural network. Unlike the backpropagation (BP) algorithm often used, our training algorithm can realize global optimization. Simulations show the effectiveness of our approach.