2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)最新文献_第4页

Message from the DSN 2022 Workshop Chairs 来自DSN 2022研讨会主席的信息

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-06-01 DOI: 10.1109/dsn-w54100.2022.00006

引用次数: 0

Certify the Uncertified: Towards Assessment of Virtualization for Mixed-criticality in the Automotive Domain 认证未认证:面向汽车领域混合关键的虚拟化评估

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-05-25 DOI: 10.48550/arXiv.2205.12596

M. Cinque, L. Simone, Andrea Marchetta

引用次数: 2

Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems 信息物理系统中数据和知识驱动异常检测的鲁棒性测试

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2022-04-20 DOI: 10.48550/arXiv.2204.09183

Xugui Zhou, Maxfield Kouzel, H. Alemzadeh

{"title":"Robustness Testing of Data and Knowledge Driven Anomaly Detection in Cyber-Physical Systems","authors":"Xugui Zhou, Maxfield Kouzel, H. Alemzadeh","doi":"10.48550/arXiv.2204.09183","DOIUrl":"https://doi.org/10.48550/arXiv.2204.09183","url":null,"abstract":"The growing complexity of Cyber-Physical Systems (CPS) and challenges in ensuring safety and security have led to the increasing use of deep learning methods for accurate and scalable anomaly detection. However, machine learning (ML) models often suffer from low performance in predicting unexpected data and are vulnerable to accidental or malicious perturbations. Although robustness testing of deep learning models has been extensively explored in applications such as image classification and speech recognition, less attention has been paid to ML-driven safety monitoring in CPS. This paper presents the preliminary results on evaluating the robustness of ML-based anomaly detection methods in safety-critical CPS against two types of accidental and malicious input perturbations, generated using a Gaussian-based noise model and the Fast Gradient Sign Method (FGSM). We test the hypothesis of whether integrating the domain knowledge (e.g., on unsafe system behavior) with the ML models can improve the robustness of anomaly detection without sacrificing accuracy and transparency. Experimental results with two case studies of Artificial Pancreas Systems (APS) for diabetes management show that ML-based safety monitors trained with domain knowledge can reduce on average up to 54.2% of robustness error and keep the average F1 scores high while improving transparency.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129463024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Autonomous Attack Mitigation for Industrial Control Systems 工业控制系统的自主攻击缓解

2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W) Pub Date : 2021-11-03 DOI: 10.1109/dsn-w54100.2022.00015

John Mern, K. Hatch, Ryan Silva, Cameron Hickert, Tamim I. Sookoor, Mykel J. Kochenderfer

{"title":"Autonomous Attack Mitigation for Industrial Control Systems","authors":"John Mern, K. Hatch, Ryan Silva, Cameron Hickert, Tamim I. Sookoor, Mykel J. Kochenderfer","doi":"10.1109/dsn-w54100.2022.00015","DOIUrl":"https://doi.org/10.1109/dsn-w54100.2022.00015","url":null,"abstract":"Defending industrial control systems and other networks from cyber attack requires timely responses to alerts and threat intelligence. Decisions about how to respond involve coordinating actions across multiple nodes based on imperfect indicators of compromise while minimizing disruptions to network operations. Currently, playbooks are used to automate portions of a response process, but often leave complex decision-making to a human analyst. In this work, we present a deep reinforcement learning approach to autonomous response and recovery in large industrial control networks. We propose an attention-based neural architecture that is flexible to the size of the network under protection. To train and evaluate the autonomous defender agent, we present an industrial control network simulation environment suitable for reinforcement learning. Experiments show that the learned agent can effectively mitigate advanced attacks that progress with few observable signals over several months before execution. The proposed application of AI/ML techniques for security outperforms a fully automated playbook method in simulation, taking less disruptive actions while also defending more nodes on the network. The learned policy is also more robust to changes in attacker behavior than playbook approaches.","PeriodicalId":349937,"journal":{"name":"2022 52nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129153609","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1