Recent studies have revealed the vulnerability of graph neural networks (GNNs) to adversarial poisoning attacks on node classification tasks. Current defensive methods require substituting the original GNNs with defense models, regardless of the original's type. This approach, while targeting adversarial robustness, compromises the enhancements developed in prior research to boost GNNs' practical performance. Here we introduce Grimm, the first plug-and-play defense model. With just a minimal interface requirement for extracting features from any layer of the protected GNNs, Grimm is thus enabled to seamlessly rectify perturbations. Specifically, we utilize the feature trajectories (FTs) generated by GNNs, as they evolve through epochs, to reflect the training status of the networks. We then theoretically prove that the FTs of victim nodes will inevitably exhibit discriminable anomalies. Consequently, inspired by the natural parallelism between the biological nervous and immune systems, we construct Grimm, a comprehensive artificial immune system for GNNs. Grimm not only detects abnormal FTs and rectifies adversarial edges during training but also operates efficiently in parallel, thereby mirroring the concurrent functionalities of its biological counterparts. We experimentally confirm that Grimm offers four empirically validated advantages: 1) Harmlessness, as it does not actively interfere with GNN training; 2) Parallelism, ensuring monitoring, detection, and rectification functions operate independently of the GNN training process; 3) Generalizability, demonstrating compatibility with mainstream GNNs such as GCN, GAT, and GraphSAGE; and 4) Transferability, as the detectors for abnormal FTs can be efficiently transferred across different systems for one-step rectification.

End-to-end training with global optimization have popularized graph neural networks (GNNs) for node classification, yet inadvertently introduced vulnerabilities to adversarial edge-perturbing attacks. Adversaries can exploit the inherent opened interfaces of GNNs' input and output, perturbing critical edges and thus manipulating the classification results. Current defenses, due to their persistent utilization of global-optimization-based end-to-end training schemes, inherently encapsulate the vulnerabilities of GNNs. This is specifically evidenced in their inability to defend against targeted secondary attacks. In this paper, we propose the Graph Agent Network (GAgN) to address the aforementioned vulnerabilities of GNNs. GAgN is a graph-structured agent network in which each node is designed as an 1-hop-view agent. Through the decentralized interactions between agents, they can learn to infer global perceptions to perform tasks including inferring embeddings, degrees and neighbor relationships for given nodes. This empowers nodes to filtering adversarial edges while carrying out classification tasks. Furthermore, agents' limited view prevents malicious messages from propagating globally in GAgN, thereby resisting global-optimization-based secondary attacks. We prove that single-hidden-layer multilayer perceptrons (MLPs) are theoretically sufficient to achieve these functionalities. Experimental results show that GAgN effectively implements all its intended capabilities and, compared to state-of-the-art defenses, achieves optimal classification accuracy on the perturbed datasets.

The multiobjective immune optimization algorithms (MOIAs) utilize the principle of clonal selection, iteratively evolving by replicating a small number of superior solutions to optimize decision vectors. However, this method often leads to a lack of diversity and is particularly ineffective when facing large‐scale optimization problems. Moreover, an overemphasis on elite solutions may result in a large number of redundant offspring, reducing evolutionary efficiency. By delving into the causes of these issues, we find that a key factor is that existing algorithms overlook the role of weak solutions during the evolutionary process. With this in mind, we propose a weak population–empowered large‐scale multiobjective immune algorithm (WP–MOIA). The core of this algorithm is to construct, in addition to the traditional elite population, a cooperative evolutionary population based on a portion of the remaining solutions, referred to as the weak population. During the evolution, both populations work together: the elite population maximizes its advantageous status for local searches, focusing on exploitation, while the weak population seeks greater variation to escape its disadvantaged position, engaging in broader exploration. At the same time, the sizes of both populations are dynamically adjusted to collaboratively maintain the balance of evolution. Through comparisons with nine state‐of‐the‐art multiobjective evolutionary algorithms (MOEAs) and four powerful MOIAs on 30 benchmark problems, the proposed algorithm demonstrates superior performance in both small‐scale and large‐scale multiobjective optimization problems (MOPs), and exhibits better convergence efficiency. Especially in large‐scale MOPs, the new algorithm’s performance nearly surpasses all 13 advanced algorithms being compared.

SCADA (Supervisory Control and Data Acquisition) systems, as the core of industrial control systems and widely deployed in the nation’s critical industrial infrastructure, are attractive targets for malicious hackers due to their strategic importance. According to Check Point Research, 96% of daily cyberattacks targeting industrial control systems worldwide are known to be repeat attacks. Although current research on virus propagation assists operators in mitigating the damage caused by industrial viruses to SCADA systems, these modeling methods often fail to distinguish between initial and secondary virus invasions, making them unsuitable for modeling the repeated infection spread of industrial viruses. In order to solve this problem, we propose an immune memory-empowered SCADA-based industrial virus dynamic re-propagation model MLBRM (Memory- Latent- Broken- Robust- Memory). First, by introducing an M node, the model is used to realize the function of memorizing viral strains and to quickly immunize against and eliminate them. Besides, we perform dynamic analysis of the model and conduct the second invasion analysis to demonstrate the effect of the M nodes on suppressing the spread of the virus. Additionally, we conduct a model comparison experiment and perform simulations on the US power grid real dataset to demonstrate the effectiveness of the proposed model. Finally, we draw a conclusion and provide some advice for SCADA network operators to better protect the SCADA systems.

Cache side-channel attacks have become more sophisticated and more destructive to the security of computer architectures and cloud platforms than ever before, resulting in the leakage of privacy information. Prior efforts focused on designing countermeasures instead of timely detection. To address the challenges introduced by cache side-channel attacks, anomaly detection and feature detection were proposed. However, these methods have drawbacks in terms of computational performance and detection effectiveness. In this article, we proposed Cache Side-Channel Attack Detector(CSCAD), a novel tool for detecting cache side-channel attacks against memory events in real time. Specifically, we design a collector using Hardware Performance Counters and use improved Maximum Information Coefficient to generate feature vectors. Meanwhile, an adaptive genetic algorithm with crossover and mutation probability is proposed to optimize hyperparameters of LightGBM. Additionally, an adaptive loss function weight model with low overhead is introduced to enhance efficiency of attack detection. It is encouraging to see that CSCAD achieved a recall of 98.14%. In detecting 1000 samples, it boosted the detection speed by approximately 75% compared to conventional machine learning methods. CSCAD has outperformed the state-of-the-art methods by simultaneously achieving excellent detection speed and effectiveness.

The evolving unknown cyberattacks, compounded by the widespread emerging technologies (say 5G, Internet of Things, etc.), have rapidly expanded the cyber threat landscape. However, most existing intrusion detection systems (IDSs) are effective in detecting only known cyberattacks, because only known cyberattack samples are usually available for IDS training. Identifying unknown cyberattacks, therefore, remains a big challenging issue. To meet this gap, in this paper, motivated by artificial immunity (AIm) and differential evolution (DE), we propose a bidirectional differential evolution based unknown cyberattack detection system, coined BDE-IDS. Specifically, we first design a bidirectional differential evolution algorithm for known nonself antigens (abnormal data), where bidirectional evolutionary directions are considered for increasing or decreasing the differences between known nonself antigens and self antigens (normal data), to create new antigens possibly used for generating cyberattack detectors. Second, a novel tolerance training mechanism is developed to eliminate invalid newly-evolved antigens falling into the coverage of either known self or nonself antigens. Third, the remaining antigens are employed to generate detectors for unknown cyberattacks. Extensive experiments demonstrate that the proposed BDE-IDS achieves outperformance in detecting unknown cyberattacks (as well as known cyberattacks) compared to state-of-the-art studies, including those AIm-based, signature-based, and anomaly-based IDSs.

With the continuous development of cyber-attack technologies, attackers increasingly exploit zero-day vulnerabilities or leverage emerging techniques to launch sophisticated attacks, resulting in the persistent emergence of unknown cyber-attacks. However, traditional DL-based cyber-attack detection methods heavily rely on large-scale labeled training data. In practice, obtaining sufficient samples of unknown attacks is challenging, which makes it difficult for these methods to effectively defend against unknown cyber-attacks. In this paper, we propose a method for discovering unknown cyber threats empowered by genetic evolution without prior knowledge. Specifically, We, first mapped the network feature space into a gene framework, and divided the attack genes into a static gene region (SGZ) and a dynamic gene region (DGZ) according to the importance of the cyber-attack genes. Subsequently, leveraging the known attack genes, we utilized different gene evolution strategies and a Convolutional Autoencoder (CAE) to generate attack variants and potential unknown attack genes. Finally, we constructed a cyber-attack detection model incorporating both the global attention mechanism (GAM) and the local attention mechanism (LAM). The generated attack variants and unknown attack genes are the used to enhance the detection ability of the detection model for variants and unknown cyber-attacks. We conducted a large number of experiments on six real and authoritative network datasets. The experimental results show that in different scenario settings, the F1 scores of our proposed method for detecting unknown attacks are 84.64% and 95.77% respectively. The F1 score for detecting unknown attacks on the UNSW-NB15 dataset exceeds that of the baseline classifier. The F1 score for detecting unknown attacks on the CSE-CIC-IDS2018 dataset is 98.85%. In comparison with SOTA methods, the average F1 score is improved by 3.14%. In the evaluation of variant detection performance, the generation method we proposed improves the detection of variants by approximately 11.2%, surpassing generation methods such as the Conditional Generative Adversarial Network (CGAN) and the Variational Autoencoder (VAE). Meanwhile, we also comprehensively evaluated the generalization ability of our proposed method and the evolution ability of different evolution strategies on different datasets and through ablation experiments.

Graph neural networks (GNNs) have recently been shown to be vulnerable to adversarial attacks, where slight perturbations in the graph structure can lead to erroneous predictions. However, current robust models for defending against such attacks inherit the transductive limitations of graph convolutional networks (GCNs). As a result, they are constrained by fixed structures and do not naturally generalize to unseen nodes. Here, we discover that transductive GCNs inherently possess a distillable robustness, achieved through a wave-induced resonance process. Based on this, we foster this resonance to facilitate inductive and robust learning. Specifically, we first prove that the signal formed by GCN-driven message passing (MP) is equivalent to the edge-based Laplacian wave, where, within a wave system, resonance can naturally emerge between the signal and its transmitting medium. This resonance provides inherent resistance to malicious perturbations inflicted on the signal system. We then prove that merely three MP iterations within GCNs can induce signal resonance between nodes and edges, manifesting as a coupling between nodes and their distillable surrounding local subgraph. Consequently, we present Graph Resonance-fostering Network (GRN) to foster this resonance via learning node representations from their distilled resonating subgraphs. By capturing the edge-transmitted signals within this subgraph and integrating them with the node signal, GRN embeds these combined signals into the central node's representation. This node-wise embedding approach allows for generalization to unseen nodes. We validate our theoretical findings with experiments, and demonstrate that GRN generalizes robustness to unseen nodes, whilst maintaining state-of-the-art classification accuracy on perturbed graphs. Appendices can be found on arXiv version: https://arxiv.org/abs/2312.08651

With the widespread application of digital assets and the rapid development of blockchain technology, achieving secure and efficient transactions between different blockchain networks has become an urgent challenge. Existing cross-chain methods impose limitations, e.g., hash lock technology exhibits low scalability, side-chain technology is overly complex, and notary schemes pose centralization risks. In order to address these issues, we propose a cross-chain transaction solution based on proxy re-signature technology. To tackle the centralization concerns, we employ proxy re-signature technology to decentralize the authority of notaries among transaction participants, minimizing the potential for centralization at a low cost. We further present an extended scheme that can guarantee more requirements such as higher transaction amount and shorter transaction time. Furthermore, we analyze and compare the signature technologies used in the proposed solution and provide a systematic proof of our approach’s security.

Abstract The problem of data imbalance is common in reality, which greatly affects the performance of classifiers. Most of the solutions are to balance the data set by generating new minority class samples, which are faced with the problems of selecting the appropriate area for generating samples, fuzzy classification boundary and uneven distribution of samples. To solve these problems, we propose a novel oversampling algorithm named space partitioning adaptive weighted synthetic minority oversampling technique (SPAW-SMOTE). We first divide the data space into boundary space and non-boundary space based on spatial partitioning techniques. The number of samples to be generated is assigned to different spaces by the designed adaptive weighting algorithm, which is used to solve the problems of uneven distribution of samples and easy to blur the classification boundary. Finally, we also endeavor to develop a new generation algorithm to reduce the probability of overlapping samples generated when synthesizing new samples and to ensure the diversity of new samples. Experimental results on 18 real-world data sets show that the average performance (G-mean, F1-measure and Area Under Curve) of SPAW-SMOTE is significantly better than other existing oversampling techniques.

Abstract Cyber Range is an experimental platform based on virtualization technology to construct a controlled simulation environment, providing a real-world simulation environment for cybersecurity personnel to conduct various practical exercises. The problem is that generating a virtual environment satisfying the requirements is labor-intensive and time-consuming. To resolve the above problem, this paper proposes a system to automate the deployment of a cyber range. In our method, the first step is to collect virtual machines (VMs) related to cybersecurity and extract relevant features. Then, machine learning is used to classify VMs to reduce the cost of manual VMs selection. Lastly, leveraging the popular OpenStack cloud platform as the deployment platform enhances the applicability of the cyber range. When it comes time to deploy a virtual environment, the instructor only needs to provide some brief description information of a virtual environment. Then, the system will automatically parse the description file to complete the automated deployment of the virtual environment. This system has been successfully applied to the cyber range of Sichuan University for daily teaching tasks.

Application‐layer distributed denial of service (DDoS) attacks have become the main threat to Web server security. Because application‐layer DDoS attacks have strong concealability and high authenticity, intrusion detection technologies that rely solely on judging client authenticity cannot accurately detect such attacks. In addition, application‐layer DDoS attacks are periodic and repetitive, and attack targets suddenly in a short period. In this study, we propose an efficient application‐layer DDoS detection system based on improved random forest. Firstly, the Web logs are preprocessed to extract the user session characteristics. Subsequently, we propose a Session Identification based on Separation and Aggregation (SISA) method to accurately capture user sessions. Lastly, we propose an improved random forest classification algorithm based on feature weighting to address the issue of an increasing number of features leading to prolonged calculation times in the random forest algorithm, and as the feature dimension increases, there might be instances where no subfeature is related to the category to be classified. More importantly, we compare the request source IP with the malicious IP in the threat intelligence library to deal with the periodicity and repetition of application‐layer DDoS attacks. We conducted a comprehensive experiment on the publicly available Web log dataset and the threat intelligence database of the laboratory as well as the simulated generated attack log dataset in the laboratory environment. The experimental results show that the proposed detection system can control the false alarm rate and false alarm rate within a reasonable range, improving the detection efficiency further, the detection rate is 99.85%. In secondary attack detection experiments, our proposed detection method achieves a higher detection rate in a shorter time.

Unmanned aerial vehicles (UAVs) have experienced rapid development, permeating diverse domains. However, addressing security challenges in UAV networks remains daunting due to resource limitations and the high autonomy of UAV terminals. The current research on the UAV network intrusion detection lacks an efficient process covering each UAV terminal and a lightweight collaborative response mechanism between the UAVs and ground stations, which affects the performance of the UAV network intrusion detection. In this article, inspired by the vaccine distribution mechanism in artificial immune systems, we propose a hierarchical UAV network intrusion detection and response approach based on the vaccine distribution. Specifically, we first implement an immune game-based negative selection algorithm at the ground station, to effectively generate vaccines covering the immune space. Then, we distribute vaccines to the UAV terminals, empowering them with intrusion detection capabilities. Finally, we introduce a collaborative response mechanism to enable the intrusion detection at the UAV terminals and perform terminal state assessments. We evaluate the performance of our proposed approach on a large number of the real UAV network data sets. The experimental results indicate that our proposed intrusion detection approach for the UAV networks at the ground stations surpasses all the baseline models. In scenarios involving air-ground coordination, our suggested collaborative response approach proves to be effective in enabling intrusion detection at the UAV terminal, facilitating timely and efficient UAV intrusion detection. Moreover, we demonstrate on the ALFA and NSL-KDD data sets that our approach excels in detecting UAV network intrusions. Particularly, on real UAV network data (ALFA), the detection rate reaches 99.05% and the accuracy is 96.13% surpassing the other models by approximately 6%.

Presents corrections to the paper, (Corrections to “A Hierarchical Unmanned Aerial Vehicle Network Intrusion Detection and Response Approach Based on Immune Vaccine Distribution”).

Supervisory Control and Data Acquisition (SCADA) systems are the core of industrial control systems and an important part of critical infrastructure. With the deployment of 5G networks around the world, SCADA systems are no longer a relatively secure and physically isolated system like in the past, but are facing huge network virus threats. In order to solve the problem that existing models ignore the communication between nodes in the system, we propose an industrial virus transmission model SELBR based on immune knowledge by simulating the function of T cells in the immune system. By introducing E node, the model is used to realize the function of information transfer between nodes. What’s more, we fit the numerical simulation results with the actual data set to verify the existence of the model, and verify the effectiveness of the model for controlling the spread of industrial viruses through model comparison experiments. Numerical results show that the model can effectively control the spread of the virus. Finally, on the basis of parameter sensitivity analysis, preventive suggestions are put forward to further strengthen the security of SCADA system.

In this article, we focus on a wireless multiuser uplink network consisting of a single antenna access point (AP) and multiple single antenna users, in which each user transmits time-sensitive confidential message to the AP in a time-division multiple access (TDMA) manner. When a user is scheduled to transmit, the other users will be regarded as potential eavesdroppers. In practical Internet of Things (IoT) applications, different users may have different requirements for throughput, and the timeliness of information needs to be guaranteed. In order to effectively adapt to these heterogeneous application requirements, the average weighted sum Age of Information (AoI) minimization problem is formulated under the premise of satisfying the minimum sampling rate requirement, power allocation constraint, and user scheduling constraint. In order to solve this problem, we first propose two stationary randomized scheduling policies, which are modeled as D/Geom/1 and Geom/Geom/1 queueing systems, respectively, and design two algorithms to find the optimal sampling period of D/Geom/1 system, the sampling probability of Geom/Geom/1 system, the power ratio allocated to confidential information, and the user scheduling probability. Second, an AoI-aware adaptive secure transmission scheme (AASTS) is proposed under Lyapunov optimization framework by transforming the original time-average weighted sum AoI minimization problem into a real-time optimization problem related to data queue state and AoI evolution of every time slot. Numerical results show that the proposed AASTS scheme can achieve better average AoI performance, and the D/Geom/1 system is superior to the Geom/Geom/1 one.

Cryptojacking is a new type of Internet of Things (IoT) attack, where an attacker hijacks the computing power of IoT devices, such as wireless routers, smart TVs, set-top boxes, or cameras, to mine cryptocurrencies, e.g., PyRoMineIoT. The attackers launch selfish mining-like (SM-like) attacks to obtain lucrative mining rewards with the stolen computing power, once the power exceeds a threshold. Generally, a single deep learning (DL) model with a single feature (e.g., fork height) is trained to detect SM-like attacks. However, the existing model fails to detect every SM-like attack since the model training ignores other distinctive features (e.g., mining rewards and blocking rate) of SM-like attacks. In this article, SM-NEEDLE, an ensemble DL (NEEDLE) method is proposed to detect SM-like attacks. More specifically, the distinctive features are extracted from the blockchain system, where SM-like simulators emulate the strategies of SM-like attacks. Further, to circumvent the local optima problem caused by the single DL model (e.g., Back-Propagation Neural Network, BPNN), the SM-NEEDLE trains multiple BPNNs with these distinctive features. Evaluation results indicate the accuracy and false negative rate (FNR) of SM-NEEDLE for detecting SM-like attacks (including SM1 and its variants) are 98.9% and 1.48%, respectively. That is, 98.9% of SM-like attacks are correctly identified and only 1.48% of attacks are undetectable.

As one of the most common web attack types, the XSS (Cross Site Scripting) attack is an important research topic in web attack and defense technology. However, the attack vectors in security evaluation methods are often based on expert experience or manual testing methods, which are not only costly and time-consuming but also have a large number of false positives. In this paper, we build an automatic XSS attack vector generation method based on the improved Dueling DDQN algorithm. First, we model the XSS attack vector generation process as a Markov decision process, mapping the initial attack vector mutation points and mutation strategies to the state space and action space of the model, respectively. Second, we propose an improved Dueling DDQN algorithm by introducing a priority experience replay mechanism to improve algorithm performance and the speed of attack vector generation. Third, we establish a feedback mechanism based on the edit distance algorithm to define the role of the reward function, preventing the model from getting stuck in local optima and achieving better mutation effects. Finally, we propose an automatic XSS attack verification method based on static semantic analysis to validate the effectiveness of our generated attack vectors. Based on the aforementioned methods, we have developed a prototype tool for automatic XSS scanning, which avoids generating a high proportion of invalid samples like traditional XSS scanners. The experimental results demonstrate that the improved Dueling DDQN algorithm outperforms other value-based reinforcement learning algorithms in terms of convergence speed, learning efficiency, and stability. The adaptive attack vector generation model can generate attack vectors that adapt to program context semantics and bypass defense mechanisms. Our method performs well when directly scanning the target system and exhibits a higher bypass rate of 85.71% in target systems deployed with WAFs. Furthermore, the model can learn the shortest path for selecting strategies to bypass WAF detection

Host-based intrusion detection systems (HIDS) have been widely acknowledged as an effective approach for detecting and mitigating malicious activities. Among various data sources utilized in HIDS, system call traces have gained significant popularity due to their inherent advantage of providing fine-grained information. Nevertheless, conventional feature extraction techniques relying on system calls tend to overlook the issue of high-dimensional sparse feature space. In this paper, we conduct a theoretical analysis to investigate the underlying causes of the sparsity problem. Subsequently, we propose an anti-sparse theory (anti-ST) as a solution to address this issue. Then, we design a multi-granularity feature extraction method (MGFE), which also meets the prerequisite mathematical conditions of the anti-ST. By applying this method, we effectively reduce the size of the feature space and minimize the number of generated features, thus mitigating sparsity. Furthermore, leveraging this approach, we propose a robust and anti-sparsity host intrusion detection framework, known as the MGFE-based Host Intrusion Detection Framework (BR-HIDF). A series of experiments were conducted to evaluate the proposed framework and compare it with the state-of-the-art method. The results demonstrate that our framework achieves impressive accuracy (97.26%), precision (97.62%), recall (96.85%), and F1 score (97.23%) in the intrusion detection task, surpassing existing frameworks. Moreover, the proposed framework significantly reduces the time overhead by 38.80%, exhibiting the highest AUC value of 0.992. Furthermore, we enhance the robustness of the detection system by integrating host-based and network-based detection, which provides greater flexibility in identifying various types of attacks.

Recent studies have revealed the vulnerability of graph convolutional networks (GCNs) to edge-perturbing attacks, such as maliciously inserting or deleting graph edges. However, theoretical proof of such vulnerability remains a big challenge, and effective defense schemes are still open issues. In this article, we first generalize the formulation of edge-perturbing attacks and strictly prove the vulnerability of GCNs to such attacks in node classification tasks. Following this, an anonymous GCN, named AN-GCN, is proposed to defend against edge-perturbing attacks. In particular, we present a node localization theorem to demonstrate how GCNs locate nodes during their training phase. In addition, we design a staggered Gaussian noise-based node position generator and a spectral graph convolution-based discriminator (in detecting the generated node positions). Furthermore, we provide an optimization method for the designed generator and discriminator. It is demonstrated that the AN-GCN is secure against edge-perturbing attacks in node classification tasks, as AN-GCN is developed to classify nodes without the edge information (making it impossible for attackers to perturb edges anymore). Extensive evaluations verify the effectiveness of the general edge-perturbing attack (G-EPA) model in manipulating the classification results of the target nodes. More importantly, the proposed AN-GCN can achieve 82.7% in node classification accuracy without the edge-reading permission, which outperforms the state-of-the-art GCN.

The negative selection algorithm (NSA) is an essential algorithm in the artificial immune system used to achieve anomaly detection by generating detectors. The traditional NSA algorithm generates candidate detectors randomly, which leads to a partially dense and redundant distribution of detectors in the nonself areas, resulting in the presence of holes that are not covered by detectors. A detector generation algorithm based on particle swarm optimization (DGA-PSO) is proposed to overcome these defects. DGA-PSO converts the self-tolerance process into an adaptation function to guide particles to move in a specific direction by artificial settings and variants, generates efficient detectors covering the nonself space, reduces the redundancy among detectors and fills holes not covered. Thus, we successfully reduce the number of detectors while improving the detection rate of the algorithm. Through experimental validation analysis, DGA-PSO ranks first in detector training time and the detection rate on four UCI datasets compared to the classical algorithms RNSA and V-Detector and the improved algorithms BIORV-NSA, ADC-NSA and IFB-NSA.

Android malware and its variants are a major challenge for mobile platforms. However, there are two main problems in the existing detection methods:a) The detection method lacks the evolution ability for Android malware, which leads to the low detection rate of the detection model for malware and its variants.b) Traditional detection methods require centralized data for model training, however, the aggregation of training samples is limited due to the infectivity of malware and growing data privacy concerns, centralized detection methods are difficult to be applied in actual detection scenarios. In this paper, we propose FEDriod, a comprehensive Android malware detection method based on federated learning architecture that protects against growing Android malware or emerging Android malware variants. Specifically, we employ genetic evolution strategy to simulate the evolution of Android malware and develop potential malware variants from typical Android malware. Then, we customize the Android malware detection model based on residual neural network to achieve high detection accuracy. Finally, to achieve the protection sensitive data, we develope a federated learning framework to allows multiple Android malware detection agencies to jointly build a comprehensive Android malware detection model. We comprehensively evaluate the performance of FEDriod on the CIC, Drebin, and Contagio authoritative datasets. Experimental results show that our local model outperforms all baseline classifiers. In the federal scenario, our proposed method is superior to the state-of-the-art detection methods, especially in the cross-dataset evaluation, the F1 of FEDriod is 98.53%. More important, we performed genetic evolution experiments on the Drebin dataset, and the results showed that our proposed method has the ability to detect Android malware variants.

Feature selection algorithms aim to improve the per-formance of machine learning algorithms by removing irrelevant and redundant features. Various feature selection algorithms have been proposed, but most of them select a global feature subset for characterizing the entire sample space. In contrast, this study proposes an efficient discrete clonal selection algorithm for local feature selection called DCSA-LFS with three features: (1) local sample behaviors are considered, and a local clustering-based evaluation criterion is used to select a distinct optimized feature subset for each different sample region; (2) an improved discrete clonal selection algorithm is proposed, which uses a differential evolution-based mutation operator to enhance the search capability of clonal selection algorithms; and (3) a two-part antibody representation is adopted to automatically adjust the weight-related parameter. Experimental results on twelve UCI datasets show that DCSA-LFS is competitive with traditional filter-based feature selection algorithms and a clonal selection algorithm-based local feature selection algorithm.

Recent studies have demonstrated the potentials of federated learning (FL) in achieving cooperative and privacy-preserving data analytics. It would also be promising if FL can be employed in vehicular ad hoc networks (VANETs) for cooperative learning tasks, such as steering angle prediction, trajectory prediction, drivable road detection, etc., among integrated vehicles. However, since VANETs are characterized by ad hoc cooperating vehicles with non-independent and identically distributed (Non-IID) data, directly employing existing FL frameworks to VANETs may cause extensive communication overhead and compromised model performance. Further, most of the existing deep learning models incorporated in FL frameworks rely heavily on data with manual annotations, leading to a huge labor cost. To address these issues, in this paper we propose an efficient and effective Federated End-to-End Learning framework for cooperative learning tasks in VANETs, named FEEL. Specifically, we first formulate a distributed optimization problem for cooperative deep learning tasks with Non-IID data in multi-hop cluster VANETs. Second, two algorithms for inter-cluster learning and inner-cluster learning are respectively designed, to reduce the communication overhead and fit Non-IID data. Third, a Paillier-based communication protocol is crafted, allowing secure model parameter updates at the central server without knowing the real updates at each cooperating base station. Extensive experiments on two real-world datasets are conducted by considering various data distributions and VANET topologies, demonstrating the high efficiency and effectiveness of the proposed FEEL framework in both regression and classification tasks.

Supervisory control and data acquisition (SCADA) networks provide high situational awareness and automation control for industrial control systems, whilst introducing a wide range of access points for cyber attackers. To address these issues, a line of machine learning or deep learning based intrusion detection systems (IDSs) have been presented in the literature, where a large number of attack examples are usually demanded. However, in real-world SCADA networks, attack examples are not always sufficient, having only a few shots in many cases. In this paper, we propose a novel few-shot learning based IDS, named FS-IDS, to detect cyber attacks against SCADA networks, especially when having only a few attack examples in the defenders’ hands. Specifically, a new method by orchestrating one-hot encoding and principal component analysis is developed, to preprocess SCADA datasets containing sufficient examples for frequent cyber attacks. Then, a few-shot learning based preliminary IDS model is designed and trained using the preprocessed data. Last, a complete FS-IDS model for SCADA networks is established by further training the preliminary IDS model with a few examples for cyber attacks of interest. The high effectiveness of the proposed FS-IDS, in detecting cyber attacks against SCADA networks with only a few examples, is demonstrated by extensive experiments on a real SCADA dataset.

With the increasing popularity of digital video communication, video data hiding has become an active research topic in covert communication and privacy protection. Traditional video data hiding methods often use quantized discrete cosine transform (QDCT) coefficients to carry a sufficient payload. However, since QDCT coefficients expose texture features and motion characteristics of the present video frame heavily, data embedding with QDCT coefficients may lead to significant intra-frame distortion and inter-frame distortion drift. To avoid obvious visual artifacts and keep bit-rate within a satisfactory level of the marked video, data embedding in QDCT coefficients should take into account both the intra-frame and inter-frame distortion impacts. It motivates the authors to propose an efficient cost assignment-based video data hiding method in this paper. The proposed cost assignment method aims to accurately evaluate the data embedding distortion. Specifically, the proposed scheme considers intra-frame changes and intra-frame distortion drift, for which the texture and motion changes of frames can be measured. The frame position is also used to reflect a cumulative distortion difference of multiple frames. For data embedding, syndrome-trellis code (STC) is adopted to minimize the overall distortion. Experimental results show that the proposed method significantly outperforms existing works in terms of payload-distortion performance.

The rapid convergence of legacy industrial infrastructures with intelligent networking and computing technologies (e.g., 5G, software-defined networking, and artificial intelligence), have dramatically increased the attack surface of industrial cyber-physical systems (CPSs). However, withstanding cyber threats to such large-scale, complex, and heterogeneous industrial CPSs has been extremely challenging, due to the insufficiency of high-quality attack examples. In this article, we propose a novel federated deep learning scheme, named DeepFed, to detect cyber threats against industrial CPSs. Specifically, we first design a new deep learning-based intrusion detection model for industrial CPSs, by making use of a convolutional neural network and a gated recurrent unit. Second, we develop a federated learning framework, allowing multiple industrial CPSs to collectively build a comprehensive intrusion detection model in a privacy-preserving way. Further, a Paillier cryptosystem-based secure communication protocol is crafted to preserve the security and privacy of model parameters through the training process. Extensive experiments on a real industrial CPS dataset demonstrate the high effectiveness of the proposed DeepFed scheme in detecting various types of cyber threats to industrial CPSs and the superiorities over state-of-the-art schemes.

Biometric image hashing techniques have been widely studied and seen progressive advancements. However, only a handful of available solutions provide two-factor cancelability while simultaneously satisfying the tradeoff among all criteria of template protection mechanisms. In this paper, we propose a novel scheme for generating a secure and robust hash from a fingerprint image using Fourier-Mellin transform and fractal coding. First, due to its invariance property, Fourier-Mellin transform is incorporated into the domain fingerprint minutiae blocks to provide feature alignment, therein generating a fixed-length minutiae representation for comparison. Then, dimensionality reduction and texture compression are exploited using fractal coding to generate a robust and compact hash for improved security and recognition. The experimental results demonstrate a favorable recognition performance on benchmarked state-of-the-art schemes from FVC2002 and FVC2004 fingerprint databases. The analyses prove our method's robustness and resiliency to security and privacy attacks. Our method also satisfies the revocability and unlinkability criteria of cancelable biometrics.

Multiuser detection (MUD) for code-division multiple-access (CDMA) systems usually relies on some a priori channel estimates, which are obtained either blindly or by using training sequences, and the covariance matrix of the received signal, usually replaced by the sample covariance matrix. However, such prior estimates are often affected by errors that are typically ignored in subsequent detection. In this paper, we present robust channel estimation and MUD techniques for multicarrier (MC) CDMA by explicitly taking into account such estimation errors. The proposed techniques are obtained by optimizing the worst case performance over two bounded uncertainty sets pertaining to the two types of estimation errors. We show that although the estimation errors associated with the prior channel estimate and the sample covariance matrix are generally not bounded, it is beneficial to optimize the worst case performance over properly chosen bounded uncertainty sets determined by a parameter called bounding probability. At a slightly higher computational complexity, our proposed robust detectors are shown to yield improved performance over the standard detectors that ignore the prior estimation errors.

A new differential modulation scheme is presented for coded orthogonal frequency-division multiplexing (OFDM) systems with multiple transmit antennas in frequency- and time-selective channels. In contrast to an earlier scheme that involves differential modulation in space and time (ST) across two code matrices, the new scheme performs it in space and frequency (SF) within only one code matrix. As such, the shortest coherence time of the channel that can be handled is reduced, which makes the differential SF scheme more resistant to fast fading. Along with a suitable spectral encoder and interleaver, both the differential ST and SF schemes offer joint spatio-spectral diversity and coding gain. Numerical simulation confirms that SF is indeed more resistant to time-selective fading than ST; however, the former also suffers some performance loss caused by frequency-selective fading and is preferred only when fast fading is prevalent.

In this paper, we present a novel code-timing estimator for uplink asynchronous direct-sequence code-division multiple-access systems utilizing bandlimited chip waveforms. The proposed estimator requires only the spreading code and training of the desired user. We start from a maximum likelihood (ML) approach that models the intersymbol interference and multiple-access interference as a colored Gaussian process with unknown covariance matrix in the frequency domain. The exact ML estimator is highly nonlinear and requires iterative searches over multi-dimensional parameter space that is impractical to implement. To deal with this difficulty, we invoke asymptotic (large-sample) approximations of the ML criterion and reparameterization techniques, which lead to an asymptotic ML estimator that yields code-timing and channel estimates via efficient noniterative quadratic optimizations. To benchmark the proposed estimator, we provide Crame/spl acute/r-Rao bound analysis for the code-timing estimation problem. Numerical simulation results are presented, which show that the proposed scheme is resistant to interference, fading, and modeling errors (e.g., sampling position errors), and compares favorably to several competing schemes in multipath fading channels.