Search Results (3,771)

Moving target defense (MTD) technology baffles potential attacks by dynamically changing the software in use and/or its configuration while maintaining the application’s running states. But it incurs a deployment cost and various performance overheads, degrading performance. An attack graph is capable of evaluating the balance between the effectiveness and cost of an MTD deployment. In this study, we consider a network scenario in which each node in the attack graph can deploy MTD technology. We aim to achieve MTD deployment effectiveness optimization (MTD-DO) in terms of minimizing the network security loss under a limited budget. The existing related works either considered only a single node for deploying an MTD or they ignored the deployment cost. We first establish a non-linear MTD-DO formulation. Then, two deep reinforcement learning-based algorithms are developed, namely, deep Q-learning (DQN) and proximal policy optimization (PPO). Moreover, two metrics are defined in order to effectively evaluate MTD-DO algorithms with varying network scales and budgets. The experimental results indicate that both PPO- and DQN-based algorithms perform better than Q-learning-based and random algorithms. The DQN-based algorithm converges more quickly and performs, in terms of reward, marginally better than the PPO-based algorithm. Full article

Deep Generative Models (DGMs), as a state-of-the-art technology in the field of artificial intelligence, find extensive applications across various domains. However, their security concerns have increasingly gained prominence, particularly with regard to invisible backdoor attacks. Currently, most backdoor attack methods rely on visible backdoor triggers that are easily detectable and defendable against. Although some studies have explored invisible backdoor attacks, they often require parameter modifications and additions to the model generator, resulting in practical inconveniences. In this study, we aim to overcome these limitations by proposing a novel method for invisible backdoor attacks. We employ an encoder–decoder network to ‘poison’ the data during the preparation stage without modifying the model itself. Through meticulous design, the trigger remains visually undetectable, substantially enhancing attacker stealthiness and success rates. Consequently, this attack method poses a serious threat to the security of DGMs while presenting new challenges for security mechanisms. Therefore, we urge researchers to intensify their investigations into DGM security issues and collaboratively promote the healthy development of DGM security. Full article

Although field medical microgrids have been widely studied as an important component of future medical power systems, current sharing control in field medical microgrids under false information injection (FDI) attacks has rarely been researched. Based on this, this paper proposes a distributed fuzzy control method for power sharing in field medical microgrids considering communication networks under FDI attacks. First, the field medical microgrid is modeled as a multi-bus DC microgrid system with power coupling. To provide voltage control and initial current equalization, fractional order PI control is applied. In order to reduce the model complexity, the concept of block modeling is employed to transform the model into a linear heterogeneous multi-agent system. Secondly, a fully distributed current sharing fuzzy control strategy is proposed. It can precisely realize current sharing control and reduce the communication bandwidth. Finally, the proposed control strategy is verified by simulation results. Full article

The digital transformation age introduces cybersecurity threats into the hospitality industry by increasing the exposure and vulnerability of hospitality firms’ data and systems to hackers. The hospitality industry is a diverse segment of the service sector dedicated to the provision of services in areas such as accommodation, food and beverage, travel and tourism, and recreation, including hotels, restaurants, bars, travel agencies, and theme parks. Cybersecurity risks in the hospitality industry affect the data and systems of businesses such as accommodation, food, travel, and entertainment, primarily enabled by the industry’s increasing digitization. This study aims to map the principal cybersecurity risks to the main stakeholders by proposing a novel Picture Fuzzy Sets (PFSs)-based Matrix of Alliances and Conflicts: Tactics, Objectives, and Recommendations (MACTOR) approach. The purpose here is to examine each stakeholder’s position towards handling cybersecurity attacks and estimate the uncertain nature of personal judgments of industry representatives when stating their point of view. The research aimed to extract the triggering positions of the defined cybercrime risks to reach the root cause of these risks, as the point to try to mitigate first. Thus, this paper contributes to the literature in both theoretical and practical ways by proposing a new approach and by providing real industry officials’ perspectives to solve the challenges. A hospitality practitioner can easily understand their position in this service network and take action to prevent such cybercrimes. Full article

Community detection enables the discovery of more connected segments of complex networks. This capability is essential for effective network analysis. But, it raises a growing concern about the disclosure of user privacy since sensitive information may be over-mined by community detection algorithms. To address this issue, the problem of community detection attacks has emerged to subtly perturb the network structure so that the performance of community detection algorithms deteriorates. Three scales of this problem have been identified in the literature to achieve different levels of concealment, such as target node, target community, or global attack. A broad range of community detection attack algorithms has been proposed, utilizing various approaches to tackle the distinct requirements associated with each attack scale. However, existing surveys of the field usually concentrate on studies focusing on target community attacks. To be self-contained, this survey starts with an overview of community detection algorithms used on the other side, along with the performance measures employed to evaluate the effectiveness of the community detection attacks. The core of the survey is a systematic analysis of the algorithms proposed across all three scales of community detection attacks to provide a comprehensive overview. The survey wraps up with a detailed discussion related to the research opportunities of the field. Overall, the main objective of the survey is to provide a starting and diving point for scientists. Full article

This paper presents three novel encryption and decryption schemes based on graph theory that aim to improve security and error resistance in communication networks. The novelty of this work lies in the application of complete bipartite graphs in two of the schemes and the Cartesian product of graphs in the third, representing a unique approach to cryptographic algorithm development. Unlike traditional cryptographic methods, these graph-based schemes use structural properties of graphs to achieve robust encryption, providing greater resistance to attacks and corruption. Each scheme is illustrated with detailed examples that show how the algorithms can be successfully implemented. The algorithms are written in standard mathematical notation, making them adaptable for machine implementation and scalable for real-world use. The schemes are also rigorously analyzed and compared in terms of their temporal and spatial complexities, using Big $\mathcal{O}$ notation. This comprehensive evaluation focuses on their effectiveness, providing valuable insights into their potential for secure communication in modern networks. Full article

With the frequent occurrence of natural disasters and the acceleration of urbanization, it is necessary to carry out efficient evacuation, especially when earthquakes, fires, terrorist attacks, and other serious threats occur. However, due to factors such as small targets, complex posture, occlusion, and dense distribution, the current mainstream algorithms still have problems such as low precision and poor real-time performance in crowd person detection. Therefore, this paper proposes EAAnet, a crowd person detection algorithm. It is based on YOLOv5, with CBAM (Convolutional Block Attention Module) introduced into the backbone, BiFPN (Bidirectional Feature Pyramid Network) introduced into the neck, and combined with a loss function of CIoU_Loss to better predict the person number. The experimental results show that compared with other mainstream detection algorithms, EAAnet has achieved significant improvement in precision and real-time performance. The precision value of all categories was 78.6%, which was increased by 1.8. Among these, the categories of riders and partially visible person were increased by 4.6 and 0.8, respectively. At the same time, the parameter number of EAAnet is only 7.1M, with a calculation amount of 16.0G FLOPs. Therefore, it is proved that EAAnet has the ability of the efficient real-time detection of the crowd person and is feasible in the field of emergency management. Full article

Due to their inherent openness, wireless sensor networks (WSNs) are vulnerable to eavesdropping attacks. Addressing the issue of secure Internet Key Exchange (IKE) in the absence of reliable third parties like CA/PKI (Certificate Authority/Public Key Infrastructure) in WSNs, a novel key synchronization method named NDPCS-KS is proposed in the paper. Firstly, through an initial negotiation process, both ends of the main channels generate the same initial key seeds using the Channel State Information (CSI). Subsequently, negotiation keys and a negative database (NDB) are synchronously generated at the two ends based on the initial key seeds. Then, in a second-negotiation process, the NDB is employed to filter the negotiation keys to obtain the keys for encryption. NDPCS-KS reduced the risk of information leakage, since the keys are not directly transmitted over the network, and the eavesdroppers cannot acquire the initial key seeds because of the physical isolation of their eavesdropping channels and the main channels. Furthermore, due to the NP-hard problem of reversing the NDB, even if an attacker obtains the NDB, deducing the initial key seeds is computationally infeasible. Therefore, it becomes exceedingly difficult for attackers to generate legitimate encryption keys without the NDB or initial key seeds. Moreover, a lightweight anti-replay and identity verification mechanism is designed to deal with replay attacks or forgery attacks. Experimental results show that NDPCS-KS has less time overhead and stronger randomness in key generation compared with other methods, and it can effectively counter replay, forgery, and tampering attacks. Full article

Background: Concerns have been raised regarding the effects of perfluoroalkyl substance (PFAS) exposure on cardiovascular diseases (CVD), but clear evidence linking PFAS exposure to CVD is lacking, and the mechanism remains unclear. Objectives: To study the association between PFASs and CVD in U.S. population, and to reveal the mechanism of PFASs’ effects on CVD. Methods: To assess the relationships between individual blood serum PFAS levels and the risk of total CVD or its subtypes, multivariable logistic regression analysis and partial least squares discriminant analysis (PLS-DA) were conducted on all participants or subgroups among 3391 adults from the National Health and Nutrition Examination Survey (NHANES). The SuperPred and GeneCards databases were utilized to identify potential targets related to PFAS and CVD, respectively. Gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses of intersection genes were performed using Metascape. Protein interaction networks were generated, and core targets were identified with STRING. Molecular docking was achieved using Autodock Vina 1.1.2. Results: There was a positive association between Me-PFOSA-AcOH and CVD (OR = 1.28, p = 0.022), especially coronary heart disease (CHD) (OR = 1.47, p = 0.007) and heart attack (OR = 1.58, p < 0.001) after adjusting for all potential covariates. Me-PFOSA-AcOH contributed the most to distinguishing between individuals in terms of CVD and non-CVD. Significant moderating effects for Me-PFOSA-AcOH were observed in the subgroup analysis stratified by sex, ethnicity, education level, PIR, BMI, smoking status, physical activity, and hypertension (p < 0.05). The potential intersection targets were mainly enriched in CVD-related pathways, including the inflammatory response, neuroactive ligand–receptor interaction, MAPK signaling pathway, and arachidonic acid metabolism. TLR4 was identified as the core target for the effects of Me-PFOSA-AcOH on CVD. Molecular docking results revealed that the binding energy of Me-PFOSA-AcOH to the TLR4-MD-2 complex was −7.2 kcal/mol, suggesting that Me-PFOSA-AcOH binds well to the TLR4-MD-2 complex. Conclusions: Me-PFOSA-AcOH exposure was significantly associated with CVD. Network toxicology and molecular docking uncovered novel molecular targets, such as TLR4, and identified the inflammatory and metabolic mechanisms underlying Me-PFOSA-AcOH-induced CVD. Full article

Software-Defined Networking (SDN) has emerged as a revolutionary architecture in computer networks, offering comprehensive network control and monitoring capabilities. However, securing the east–west interface, which is crucial for communication between distributed SDN controllers, remains a significant challenge. This study proposes a novel blockchain-based security framework that integrates Ethereum technology with customized blockchain algorithms for authentication, encryption, and access control. The framework introduces decentralized mechanisms to protect against diverse attacks, including false data injection, man-in-the-middle (MitM), and unauthorized access. Experimental results demonstrate the effectiveness of this framework in securing distributed controllers while maintaining high network performance and low latency, paving the way for more resilient and trustworthy SDN infrastructures. Full article

Heart disease remains a leading cause of mortality worldwide, and the timely and accurate prediction of heart attack is crucial yet challenging due to the complexity of the condition and the limitations of traditional diagnostic methods. These challenges include the need for resource-intensive diagnostics and the difficulty in interpreting complex predictive models in clinical settings. In this study, we apply and compare the performance of five well-known Deep Learning (DL) models, namely Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a Hybrid model, to a heart attack prediction dataset. Each model was properly tuned and evaluated using accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC) as performance metrics. Additionally, by integrating an Explainable Artificial intelligence (XAI) technique, specifically Shapley Additive Explanations (SHAP), we enhance the interpretability of the predictions, making them actionable for healthcare professionals and thereby enhancing clinical applicability. The experimental results revealed that the Hybrid model prevailed, achieving the highest performance across all metrics. Specifically, the Hybrid model attained an accuracy of 91%, precision of 89%, recall of 90%, F1-score of 89%, and an AUC of 0.95. These results highlighted the Hybrid model’s superior ability to predict heart attacks, attributed to its efficient handling of sequential data and long-term dependencies. Full article

Machine learning systems, particularly in the domain of image recognition, are susceptible to adversarial perturbations applied to input data. These perturbations, while imperceptible to humans, have the capacity to easily deceive deep learning classifiers. Current defense methods for image recognition focus on using diffusion models and their variants. Due to the depth of diffusion models and the large amount of computations generated during each inference process, the GPU and storage performance of the device are extremely high. To address this problem, we propose a new defense-based non-overlapping image compression filter for image recognition classifiers against adversarial attacks. This method inserts a non-overlapping image compression filter before the classifier to make the results of the classifier invariant under subtle changes in images. This method does not weaken the adversarial robustness of the model and can reduce the computational cost during the training process of the image classification model. In addition, our method can be easily integrated with existing image classification training frameworks with only some minor adjustments. We validate our results by performing a series of experiments under three different convolutional neural network architectures (VGG16, ResNet34, and Inception-ResNet-v2) and on different datasets (CIFAR10 and CIFAR100). The experimental results show that under the Inception-ResNet-v2 architecture, our method achieves an average accuracy of up to 81.15% on the CIFAR10 dataset, fully demonstrating its effectiveness in mitigating adversarial attacks. In addition, under the WRN-28-10 architecture, our method achieves not only 91.28% standard accuracy on the CIFAR10 dataset but also 76.46% average robust accuracy. The test experiment on the model training time consumption shows that our defense method has an advantage in time cost, proving that our defense method is a lightweight and efficient defense strategy. Full article

A better understanding of protein–protein interaction (PPI) networks representing physical interactions between proteins could be beneficial for evolutionary insights as well as for practical applications such as drug development. As a statistical model for PPI networks, duplication–divergence models have been proposed, but they suffer from resulting in either very sparse networks in which most of the proteins are isolated, or in networks which are much denser than what is usually observed, having almost no isolated proteins. Moreover, in real networks, where a gene codes a protein, gene loss may occur. The loss of nodes has not been captured in duplication–divergence models to date. Here, we introduce a new duplication–divergence model which includes node loss. This mechanism results in networks in which the proportion of isolated proteins can take on values which are strictly between 0 and 1. To understand this new model, we apply strong and weak attacks to networks from duplication–divergence models with and without node loss, and compare the results to those obtained when carrying out similar attacks on two real PPI networks of E. coli and of S. cerevisiae. We find that the new model more closely reflects the damage caused by strong and weak attacks found in the PPI networks. Full article

The fast growth of the Internet has made network security problems more noticeable, so intrusion detection systems (IDSs) have become a crucial tool for maintaining network security. IDSs guarantee the normal operation of the network by tracking network traffic and spotting possible assaults, thereby safeguarding data security. However, traditional intrusion detection methods encounter several issues such as low detection efficiency and prolonged detection time when dealing with massive and high-dimensional data. Therefore, feature selection (FS) is particularly important in IDSs. By selecting the most representative features, it can not only improve the detection accuracy but also significantly reduce the computational complexity and attack detection time. This work proposes a new FS approach, BPSO-SA, that is based on the Binary Particle Swarm Optimization (BPSO) and Simulated Annealing (SA) algorithms. It combines these with the Gray Wolf Optimization (GWO) algorithm to optimize the LightGBM model, thereby building a new type of reflective Distributed Denial of Service (DDoS) attack detection model. The BPSO-SA algorithm enhances the global search capability of Particle Swarm Optimization (PSO) using the SA mechanism and effectively screens out the optimal feature subset; the GWO algorithm optimizes the hyperparameters of LightGBM by simulating the group hunting behavior of gray wolves to enhance the detection performance of the model. While showing great resilience and generalizing power, the experimental results show that the proposed reflective DDoS attack detection model surpasses conventional methods in terms of detection accuracy, precision, recall, F1-score, and prediction time. Full article

The advent of the Fourth Industrial Revolution has positioned the Internet of Things as a pivotal force in intelligent vehicles. With the source of vehicle-to-everything (V2X), Internet of Things (IoT) networks, and inter-vehicle communication, intelligent connected vehicles are at the forefront of this transformation, leading to complex vehicular networks that are crucial yet susceptible to cyber threats. The complexity and openness of these networks expose them to a plethora of cyber-attacks, from passive eavesdropping to active disruptions like Denial of Service and Sybil attacks. These not only compromise the safety and efficiency of vehicular networks but also pose a significant risk to the stability and resilience of the Internet of Vehicles. Addressing these vulnerabilities, this paper proposes a Dynamic Forest-Structured Ensemble Network (DFSENet) specifically tailored for the Internet of Vehicles (IoV). By leveraging data-balancing techniques and dimensionality reduction, the DFSENet model is designed to detect a wide range of cyber threats effectively. The proposed model demonstrates high efficacy, with an accuracy of 99.2% on the CICIDS dataset and 98% on the car-hacking dataset. The precision, recall, and f-measure metrics stand at 95.6%, 98.8%, and 96.9%, respectively, establishing the DFSENet model as a robust solution for securing the IoV against cyber-attacks. Full article