This article investigates the decentralized adaptive event-driven (AED) reliability control problem for nonlinear interconnected systems (NISs) with privacy-preserving. The decentralized optimal control strategy for the whole system is formulated by the optimal control for nominal subsystems, where an AED homomorphic cryptosystem is implemented for each subsystem to alleviate network burden while achieving security by encrypting transmitted signals. The Paillier cryptosystem with additive homomorphic properties is introduced to conceal the original data. Therefore, the transformed Hamilton–Jacobi–Bellman equations (HJBE) are constructed to facilitate cooperative optimization across subsystems within the framework of reinforcement learning. Subsequently, we leverage single critic networks to derive solutions to the HJBE, utilizing the experience replay approach for weight updates. Furthermore, by virtue of the Lyapunov function, the derived decentralized control law can force the whole NIS to be uniformly ultimately bounded stable. Eventually, numerical examples of NISs are provided to illustrate the effectiveness of the proposed optimization algorithm.
{"title":"Decentralized Event-Driven Reliability Control Using Reinforcement Learning: A Homomorphic Encryption Scheme","authors":"Jian Liu;Shuailong Wang;Jinliang Liu;Engang Tian;Chen Peng","doi":"10.1109/TR.2025.3599868","DOIUrl":"https://doi.org/10.1109/TR.2025.3599868","url":null,"abstract":"This article investigates the decentralized adaptive event-driven (AED) reliability control problem for nonlinear interconnected systems (NISs) with privacy-preserving. The decentralized optimal control strategy for the whole system is formulated by the optimal control for nominal subsystems, where an AED homomorphic cryptosystem is implemented for each subsystem to alleviate network burden while achieving security by encrypting transmitted signals. The Paillier cryptosystem with additive homomorphic properties is introduced to conceal the original data. Therefore, the transformed Hamilton–Jacobi–Bellman equations (HJBE) are constructed to facilitate cooperative optimization across subsystems within the framework of reinforcement learning. Subsequently, we leverage single critic networks to derive solutions to the HJBE, utilizing the experience replay approach for weight updates. Furthermore, by virtue of the Lyapunov function, the derived decentralized control law can force the whole NIS to be uniformly ultimately bounded stable. Eventually, numerical examples of NISs are provided to illustrate the effectiveness of the proposed optimization algorithm.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"75 ","pages":"570-580"},"PeriodicalIF":5.7,"publicationDate":"2025-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145982179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maintenance optimization is a perennially interesting subject within the field of reliability engineering, playing an essential role in enhancing the system reliability. In practice, maintenance engineers are heterogeneous with different ability levels, and maintenance failure may occur when tasks are handled by junior engineers. Inspired by the above engineering reality, this article investigates the maintenance optimization for a production system with multiple machines connected in parallel. A practical engineering scenario is studied that there is a limited number of maintenance engineers and they are categorized into different professional levels owing to diverse maintenance capabilities. In addition, the case that junior engineers cause maintenance failure with a certain probability is presented. The Markov decision process as well as Markov process are utilized to describe the operation and maintenance process of the system. When the system reaches a higher state after maintenance, it generates the higher revenue in next operation period, though at the cost of increased maintenance expenses. To balance the revenue and cost, the optimal maintenance engineer allocation and maintenance level are determined at each regular inspection epoch. With the objective of maximizing the total expected reward, a Q-learning-based reinforcement learning algorithm is employed to solve the optimal maintenance policies effectively. Finally, numerical examples are presented to validate the constructed model, and plentiful sensitivity analyses are conducted to provide scientific management proposals.
{"title":"Maintenance Optimization for Production Systems With Polytype Engineers Under Limited Maintenance Capability: A Reinforcement Learning Approach","authors":"Xian Zhao;Ru Ning;Xiaoyue Wang;Xiong Zhang","doi":"10.1109/TR.2025.3600765","DOIUrl":"https://doi.org/10.1109/TR.2025.3600765","url":null,"abstract":"Maintenance optimization is a perennially interesting subject within the field of reliability engineering, playing an essential role in enhancing the system reliability. In practice, maintenance engineers are heterogeneous with different ability levels, and maintenance failure may occur when tasks are handled by junior engineers. Inspired by the above engineering reality, this article investigates the maintenance optimization for a production system with multiple machines connected in parallel. A practical engineering scenario is studied that there is a limited number of maintenance engineers and they are categorized into different professional levels owing to diverse maintenance capabilities. In addition, the case that junior engineers cause maintenance failure with a certain probability is presented. The Markov decision process as well as Markov process are utilized to describe the operation and maintenance process of the system. When the system reaches a higher state after maintenance, it generates the higher revenue in next operation period, though at the cost of increased maintenance expenses. To balance the revenue and cost, the optimal maintenance engineer allocation and maintenance level are determined at each regular inspection epoch. With the objective of maximizing the total expected reward, a Q-learning-based reinforcement learning algorithm is employed to solve the optimal maintenance policies effectively. Finally, numerical examples are presented to validate the constructed model, and plentiful sensitivity analyses are conducted to provide scientific management proposals.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 4","pages":"5780-5791"},"PeriodicalIF":5.7,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145652147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Longyan Tan;Fanping Wei;Xiaobing Ma;Rui Peng;Hui Xiao;Li Yang
Condition-based maintenance (CBM) powered by inspection/monitoring technology is crucial to guarantee safety and economical operations of various industrial assets. The implementation of prevailing CBM procedures for large-scale heterogeneous systems, however, is increasingly challenged by model intractability and computational cost stemming from the synergistic effect of information completeness and structure complexity. In this article, we innovatively devises a tractable CBM model for multicomponent continuously degrading systems under nonperfect inspection information, which is applicable to heterogeneous system structure and arbitrary hierarchical maintenance actions. The maintenance optimization problem of interest constitutes a continuous-state partially observable Markov-decision process applicable to heterogeneous system structures. A series of structure properties associated with systematic conditional reliability and accessibility of optimal solution are established, following which a multiagent reinforcement learning model governed by partial-independent parameter-sharing mechanism is employed to allow for solution search under continuous state–action space. A customized proximal policy algorithm is then leveraged to facilitate efficient agent training by diminishing the cure of dimension. Comparative experiments conducted on train wheel treads verify the superior model performance over cost control and computational efficiency improvement.
{"title":"Systemic Condition-Based Maintenance Optimization Under Inspection Uncertainties: A Customized Multiagent Reinforcement Learning Approach","authors":"Longyan Tan;Fanping Wei;Xiaobing Ma;Rui Peng;Hui Xiao;Li Yang","doi":"10.1109/TR.2025.3583769","DOIUrl":"https://doi.org/10.1109/TR.2025.3583769","url":null,"abstract":"Condition-based maintenance (CBM) powered by inspection/monitoring technology is crucial to guarantee safety and economical operations of various industrial assets. The implementation of prevailing CBM procedures for large-scale heterogeneous systems, however, is increasingly challenged by model intractability and computational cost stemming from the synergistic effect of information completeness and structure complexity. In this article, we innovatively devises a tractable CBM model for multicomponent continuously degrading systems under nonperfect inspection information, which is applicable to heterogeneous system structure and arbitrary hierarchical maintenance actions. The maintenance optimization problem of interest constitutes a continuous-state partially observable Markov-decision process applicable to heterogeneous system structures. A series of structure properties associated with systematic conditional reliability and accessibility of optimal solution are established, following which a multiagent reinforcement learning model governed by partial-independent parameter-sharing mechanism is employed to allow for solution search under continuous state–action space. A customized proximal policy algorithm is then leveraged to facilitate efficient agent training by diminishing the cure of dimension. Comparative experiments conducted on train wheel treads verify the superior model performance over cost control and computational efficiency improvement.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 4","pages":"5848-5862"},"PeriodicalIF":5.7,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145652139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study delves into the challenge of optimizing condition-based maintenance (CBM) for $k$-out-of-$N$ systems characterized by economic dependencies, utilizing an average cost Markov decision process formalism for a detailed analysis of optimal policies. Traditionally, CBM optimization presumes a monotone control-limit policy where the degradation level of components exceeds predefined thresholds. Recent investigations have visually demonstrated that the optimal CBM policy exhibits a nonmonotone structure. Our analysis reveals that although the optimal bias functions exhibit partial monotonicity, this characteristic alone does not guarantee a monotone CBM policy. The emergence of nonmonotonicity is attributed to the dynamics of the transition matrix influenced by preventive maintenance activities. In addition, we show that the cost function is subadditive, indicating that the presence of setup costs significantly influences maintenance decisions, where this subadditivity also affects the formation of nonmonotone regions in the optimal policy. Our findings indicate that nonmonotone regions persist even in the absence of economic dependencies. Sensitivity analysis further reveals that higher cost parameters and reliability structure reduce the ratio of nonmonotone regions, enhancing system stability. This study emphasizes the complex interdependence between reliability structure and cost parameters in shaping optimal CBM policies.
{"title":"Analysis on Nonmonotone Control-Limit Condition-Based Maintenance Policies","authors":"Stephane Barde;Young Myoung Ko","doi":"10.1109/TR.2025.3582813","DOIUrl":"https://doi.org/10.1109/TR.2025.3582813","url":null,"abstract":"This study delves into the challenge of optimizing condition-based maintenance (CBM) for <inline-formula><tex-math>$k$</tex-math></inline-formula>-out-of-<inline-formula><tex-math>$N$</tex-math></inline-formula> systems characterized by economic dependencies, utilizing an average cost Markov decision process formalism for a detailed analysis of optimal policies. Traditionally, CBM optimization presumes a monotone control-limit policy where the degradation level of components exceeds predefined thresholds. Recent investigations have visually demonstrated that the optimal CBM policy exhibits a nonmonotone structure. Our analysis reveals that although the optimal bias functions exhibit partial monotonicity, this characteristic alone does not guarantee a monotone CBM policy. The emergence of nonmonotonicity is attributed to the dynamics of the transition matrix influenced by preventive maintenance activities. In addition, we show that the cost function is subadditive, indicating that the presence of setup costs significantly influences maintenance decisions, where this subadditivity also affects the formation of nonmonotone regions in the optimal policy. Our findings indicate that nonmonotone regions persist even in the absence of economic dependencies. Sensitivity analysis further reveals that higher cost parameters and reliability structure reduce the ratio of nonmonotone regions, enhancing system stability. This study emphasizes the complex interdependence between reliability structure and cost parameters in shaping optimal CBM policies.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 4","pages":"5765-5779"},"PeriodicalIF":5.7,"publicationDate":"2025-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145674669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Face recognition is a widely used authentication technology in practice, where robustness is required. It is thus essential to have an efficient and easy-to-use method for evaluating the robustness of (possibly third-party) trained face recognition systems. Existing approaches to evaluating the robustness of face recognition systems are either based on empirical evaluation (e.g., measuring attacking success rate using state-of-the-art attacking methods) or formal analysis (e.g., measuring the Lipschitz constant). While the former demands significant user efforts and expertise, the latter is extremely time-consuming. In pursuit of a comprehensive, efficient, easy-to-use, and scalable estimation of the robustness of face recognition systems, we take an old-school alternative approach and introduce RobFace, i.e., evaluation using an optimized test suite. It contains transferable adversarial face images that are designed to comprehensively evaluate a face recognition system’s robustness along a variety of dimensions. RobFace is system-agnostic and still consistent with system-specific empirical evaluation or formal analysis. We support this claim through extensive experimental results with various perturbations on multiple face recognition systems. To our knowledge, RobFace is the first system-agnostic robustness estimation test suite.
{"title":"RobFace: A Test Suite for Efficient Robustness Evaluation of Face Recognition Systems","authors":"Ruihan Zhang;Jun Sun","doi":"10.1109/TR.2025.3554575","DOIUrl":"https://doi.org/10.1109/TR.2025.3554575","url":null,"abstract":"Face recognition is a widely used authentication technology in practice, where robustness is required. It is thus essential to have an efficient and easy-to-use method for evaluating the robustness of (possibly third-party) trained face recognition systems. Existing approaches to evaluating the robustness of face recognition systems are either based on empirical evaluation (e.g., measuring attacking success rate using state-of-the-art attacking methods) or formal analysis (e.g., measuring the Lipschitz constant). While the former demands significant user efforts and expertise, the latter is extremely time-consuming. In pursuit of a comprehensive, efficient, easy-to-use, and scalable estimation of the robustness of face recognition systems, we take an old-school alternative approach and introduce <sc>RobFace</small>, i.e., evaluation using an optimized test suite. It contains transferable adversarial face images that are designed to comprehensively evaluate a face recognition system’s robustness along a variety of dimensions. <sc>RobFace</small> is system-agnostic and still consistent with system-specific empirical evaluation or formal analysis. We support this claim through extensive experimental results with various perturbations on multiple face recognition systems. To our knowledge, <sc>RobFace</small> is the first system-agnostic robustness estimation test suite.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"3615-3628"},"PeriodicalIF":5.7,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Editorial Strengthening Resilience and Security With Zero Trust","authors":"Winston Shieh","doi":"10.1109/TR.2025.3570180","DOIUrl":"https://doi.org/10.1109/TR.2025.3570180","url":null,"abstract":"","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 2","pages":"2501-2502"},"PeriodicalIF":5.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205855","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This addresses errors in [1]. Due to the error containing the count data of first officer applicants who had not answered the informed consent at that time, the following figures, tables, and texts are corrected. The corrected texts are highlighted in bold.
{"title":"Corrections to “Probabilistic Modeling of Variation in Pilot Performance during Flight Training”","authors":"Kento Yamada;Harumi Ikeshita;Yuta Kyoya;Makoto Ueno","doi":"10.1109/TR.2025.3549285","DOIUrl":"https://doi.org/10.1109/TR.2025.3549285","url":null,"abstract":"This addresses errors in [1]. Due to the error containing the count data of first officer applicants who had not answered the informed consent at that time, the following figures, tables, and texts are corrected. The corrected texts are highlighted in bold.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 2","pages":"2498-2500"},"PeriodicalIF":5.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023012","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"IEEE Reliability Society Publication Information","authors":"","doi":"10.1109/TR.2025.3570890","DOIUrl":"https://doi.org/10.1109/TR.2025.3570890","url":null,"abstract":"","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 2","pages":"C2-C2"},"PeriodicalIF":5.0,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023009","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Determination of the decision variables such as the inspection period, number of measurements, and sample size is crucial for planning an efficient degradation test. For widely used stochastic processes, the necessary and sufficient conditions for the explicit expression of optimal decision variables can be derived by minimizing the approximate variance of an estimator of interest under a limited budget. The importance of the decision variable is proposed to study the rate at which the objective function improves with the decision variable. The necessary and sufficient conditions for determining the importance of the optimal decision variables are theoretically investigated to elucidate the effect of the experimental costs and model parameters. Furthermore, the relative rankings of the importance of the optimal decision variables are illustrated through numerical examples.
{"title":"Importance Inference of Optimal Test Planning for Degradation Analysis","authors":"Yi-Shian Dong;Chien-Yu Peng","doi":"10.1109/TR.2025.3556481","DOIUrl":"https://doi.org/10.1109/TR.2025.3556481","url":null,"abstract":"Determination of the decision variables such as the inspection period, number of measurements, and sample size is crucial for planning an efficient degradation test. For widely used stochastic processes, the necessary and sufficient conditions for the explicit expression of optimal decision variables can be derived by minimizing the approximate variance of an estimator of interest under a limited budget. The importance of the decision variable is proposed to study the rate at which the objective function improves with the decision variable. The necessary and sufficient conditions for determining the importance of the optimal decision variables are theoretically investigated to elucidate the effect of the experimental costs and model parameters. Furthermore, the relative rankings of the importance of the optimal decision variables are illustrated through numerical examples.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"4426-4440"},"PeriodicalIF":5.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998201","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qing Huang;Yu He;Zhenchang Xing;Min Yu;Xiwei Xu;Qinghua Lu
Smart contracts, which automatically execute transactions based on predefined conditions, play a crucial role in asset and money exchanges. Due to their involvement in significant financial transactions, these contracts are attractive targets for hackers, leading to substantial financial losses through exploitable vulnerabilities. While various program analysis methods such as Oyente, Mythril, and Securify have been proposed to address these security concerns, they rely on rule-based patterns that are time-consuming to develop and offer limited coverage. Deep learning methods present an alternative by automatically learning code features to detect vulnerabilities. However, existing approaches face critical challenges, including feature limitations and lack of interpretability. To address these gaps, we propose the interpretable smart contract vulnerability detector, a Graph Isomorphism Network (GIN)-based vulnerability prediction model for smart contracts, enhanced with code subgraph explanations. Our approach identifies and incorporates 43 domain-specific features, augmenting GIN with domain knowledge attention mechanisms to improve vulnerability prediction. In addition, we develop an interpreter called SubgraphV, which provides explanations for vulnerability predictions through interpreted subgraphs. Our model demonstrates superior performance over traditional tools, achieving F1 score improvements from 0.254 to 0.489 on a dataset of 103 smart contract function vulnerabilities. SubgraphV outperforms existing explainability methods like GNNexplainer, PGExplainer, and SubgraphX in pinpointing vulnerabilities, accurately reflecting vulnerability patterns, and enhancing the understanding of vulnerabilities.
{"title":"Enhancing Fine-Grained Smart Contract Vulnerability Detection Through Domain Features and Transparent Interpretation","authors":"Qing Huang;Yu He;Zhenchang Xing;Min Yu;Xiwei Xu;Qinghua Lu","doi":"10.1109/TR.2025.3551356","DOIUrl":"https://doi.org/10.1109/TR.2025.3551356","url":null,"abstract":"Smart contracts, which automatically execute transactions based on predefined conditions, play a crucial role in asset and money exchanges. Due to their involvement in significant financial transactions, these contracts are attractive targets for hackers, leading to substantial financial losses through exploitable vulnerabilities. While various program analysis methods such as Oyente, Mythril, and Securify have been proposed to address these security concerns, they rely on rule-based patterns that are time-consuming to develop and offer limited coverage. Deep learning methods present an alternative by automatically learning code features to detect vulnerabilities. However, existing approaches face critical challenges, including feature limitations and lack of interpretability. To address these gaps, we propose the interpretable smart contract vulnerability detector, a Graph Isomorphism Network (GIN)-based vulnerability prediction model for smart contracts, enhanced with code subgraph explanations. Our approach identifies and incorporates 43 domain-specific features, augmenting GIN with domain knowledge attention mechanisms to improve vulnerability prediction. In addition, we develop an interpreter called SubgraphV, which provides explanations for vulnerability predictions through interpreted subgraphs. Our model demonstrates superior performance over traditional tools, achieving F1 score improvements from 0.254 to 0.489 on a dataset of 103 smart contract function vulnerabilities. SubgraphV outperforms existing explainability methods like GNNexplainer, PGExplainer, and SubgraphX in pinpointing vulnerabilities, accurately reflecting vulnerability patterns, and enhancing the understanding of vulnerabilities.","PeriodicalId":56305,"journal":{"name":"IEEE Transactions on Reliability","volume":"74 3","pages":"4207-4221"},"PeriodicalIF":5.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144998071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：