Proceedings of the 9th ACM Cyber-Physical System Security Workshop最新文献

PAID: Perturbed Image Attacks Analysis and Intrusion Detection Mechanism for Autonomous Driving Systems 自动驾驶系统的扰动图像攻击分析及入侵检测机制

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3594273

Ko Zheng Teng, Trupil Limbasiya, F. Turrin, Y. Aung, Sudipta Chattopadhyay, Jianying Zhou, M. Conti

{"title":"PAID: Perturbed Image Attacks Analysis and Intrusion Detection Mechanism for Autonomous Driving Systems","authors":"Ko Zheng Teng, Trupil Limbasiya, F. Turrin, Y. Aung, Sudipta Chattopadhyay, Jianying Zhou, M. Conti","doi":"10.1145/3592538.3594273","DOIUrl":"https://doi.org/10.1145/3592538.3594273","url":null,"abstract":"Modern Autonomous Vehicles (AVs) leverage road context information collected through sensors (e.g., LiDAR, radar, and camera) to support the automated driving experience. Once such information is collected, a neural network model predicts subsequent actions that the AV executes. However, state-of-the-art research findings have shown the possibility that an attacker can compromise the accuracy of the neural network model in predicting tasks. Indeed, mispredicting the subsequent actions can cause harmful consequences to the road user’s safety. In this paper, we analyze the disruptive impact of adversarial attacks on road context-aware Intrusion Detection System (RAIDS) and propose a solution to mitigate such effects. To this end, we implement five state-of-the-art evasion attacks on vehicle camera images the IDS uses to monitor internal vehicular traffic. Our experimental results underline how this type of attack can reduce the attack detection accuracy of such detectors down to 2.83%. To combat such adversarial attacks, we investigate different countermeasure and propose PAID, a robust context-aware IDS that leverage feature squeezing and GPS to detect intrusions. We evaluate PAID’s capability in identifying such attacks, and implementation results confirm that PAID achieves a detection accuracy of up to 93.9%, outperforming RAIDS’s performance.","PeriodicalId":324790,"journal":{"name":"Proceedings of the 9th ACM Cyber-Physical System Security Workshop","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134159932","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: 0

Digital twins: Double Insecurity for Industrial Scenarios 数字孪生:工业场景的双重不安全

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3607806

Cristina Alcaraz

引用次数: 0

Anomaly Detection Framework for Securing Next Generation Networks of Platoons of Autonomous Vehicles in a Vehicle-to-Everything System 车辆对一切系统中下一代自动驾驶车辆排网络安全的异常检测框架

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3594274

Sazid Nazat, Mustafa Abdallah

引用次数: 0

A Practical Intrusion Detection System Trained on Ambiguously Labeled Data for Enhancing IIoT Security 基于模糊标记数据训练的入侵检测系统增强工业物联网安全

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3594270

Wenzhuo Yang, Zhaowei Chu, Jiani Fan, Ziyao Liu, Kwok-Yan Lam

{"title":"A Practical Intrusion Detection System Trained on Ambiguously Labeled Data for Enhancing IIoT Security","authors":"Wenzhuo Yang, Zhaowei Chu, Jiani Fan, Ziyao Liu, Kwok-Yan Lam","doi":"10.1145/3592538.3594270","DOIUrl":"https://doi.org/10.1145/3592538.3594270","url":null,"abstract":"As a special class of the Internet-of-Things (IoT), Industrial Internet-of-Things (IIoT) enhance the efficiency of manufacturing and industrial processes by utilizing smart components and new technologies in industrial sectors. With the increasing maturity and affordability of IIoT, more and more industrial control systems and cyber-physical systems have been transformed to adopt the IIoT paradigm. The large amount of security-critical and privacy-sensitive data captured by IIoT systems are lucrative targets of, and vulnerable to, cyber-attacks, hence demanding effective protection and security control. As one of the most important tools in the detective security regime, intrusion detection systems (IDS) are thus valuable for protecting IIoT infrastructure. Many machine-learning (ML) techniques have been studied extensively to develop efficient and intelligent IDSs. Despite their popularity, most current ML-based intrusion detection systems encounter difficulties when put into practice in real industrial settings. These difficulties include the high cost of continuously obtaining accurate labels under the big data background and unsatisfactory detection results on imbalanced data sets. Hence, this paper proposes a novel method that explores the possibility of applying partial label learning (PLL) techniques jointly with data resampling algorithms to develop a practical intrusion detection system for enhancing IIoT security. Extensive experimental results on five publicly available IDS evaluation datasets clearly show the effectiveness of the proposed approach and its ability to mitigate the impact of ambiguous labels and data imbalance problems in ML-based IIoT attack detection tasks.","PeriodicalId":324790,"journal":{"name":"Proceedings of the 9th ACM Cyber-Physical System Security Workshop","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134220805","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: 0

Preventing Reverse Engineering of Control Programs in Industrial Control Systems 防止工业控制系统控制程序的逆向工程

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3594275

Shalini Banerjee, S. Galbraith, Tariq Khan, J. H. Castellanos, G. Russello

{"title":"Preventing Reverse Engineering of Control Programs in Industrial Control Systems","authors":"Shalini Banerjee, S. Galbraith, Tariq Khan, J. H. Castellanos, G. Russello","doi":"10.1145/3592538.3594275","DOIUrl":"https://doi.org/10.1145/3592538.3594275","url":null,"abstract":"Industrial Control Systems (ICS) incorporate automated control and monitoring into the industrial objectives of production, manufacturing and distribution. Programmable Logic Controllers (PLCs) are the nucleus of this framework, with control programs constituting the decision-making layer that bring about desirable changes in the process measurements. In this paper, we study the significance of pre-requisite knowledge of process control in tailoring targeted attacks. We identify a Man-At-The-End (MATE) adversary who aims at extracting the process semantics by obtaining a copy of the control program downloaded from an engineering workstation to a PLC. We focus on preventing such efforts, and present a formalization of control program abstraction and its assets, the secret values in the program that give away the operational semantics of the process. Finally, we propose , a platform that makes use of cryptographic obfuscation to secure the assets in a control program. We demonstrate an end-to-end case-study of control program formalization and present a proof-of-concept implementation of the proposed construction over two example testbeds. Our micro-benchmarks indicate that the proposed platform incurs an overall increase of 4% in the execution time for a single scan cycle, with guarantees of computational security.","PeriodicalId":324790,"journal":{"name":"Proceedings of the 9th ACM Cyber-Physical System Security Workshop","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115347795","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: 0

Blind Concealment from Reconstruction-based Attack Detectors for Industrial Control Systems via Backdoor Attacks 基于重构的工业控制系统后门攻击检测器的盲隐藏

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3594271

Tim Walita, Alessandro Erba, J. H. Castellanos, N. Tippenhauer

{"title":"Blind Concealment from Reconstruction-based Attack Detectors for Industrial Control Systems via Backdoor Attacks","authors":"Tim Walita, Alessandro Erba, J. H. Castellanos, N. Tippenhauer","doi":"10.1145/3592538.3594271","DOIUrl":"https://doi.org/10.1145/3592538.3594271","url":null,"abstract":"Industrial Control Systems (ICS) are responsible for the safety and operations of critical infrastructure such as power grids. Attacks on such systems threaten the well-being of societies, and the lives of human operators, and pose huge financial risks. To detect those attacks, process-aware attack detectors were proposed by academia and industry to verify inherent physical correlations. Such detectors will be trained by the vendors on process data from the target system, which allows malicious manipulations of the training process to later evade detection at runtime. Previously proposed attacks in this direction rely on detailed process knowledge to predict the exact attack features to be concealed. In this work, we show that even without process knowledge (i.e. being able to predict attack results), it is possible to launch training time attacks against such attack detectors. Our backdoor attacks achieve this by identifying ‘alien’ actuator state combinations that never occur in the training samples and injecting them with legitimate sensor data into the training set. At runtime, the attacker spoofs one of those alien actuator state combinations, which triggers (regardless of sensor values) the classification as ‘normal’. To demonstrate this, we design and implement five backdoor attacks against autoencoder-based anomaly detectors for 14 attacks from the BATADAL dataset collection. Our evaluation shows that our best backdoor attack implementation can achieve perfect attack concealment and accomplish an average recall of 0.19. Compared to the performance of the detector for anomalies that are not concealed by inserted triggers, our attacks decrease the detector’s recall by 0.477.","PeriodicalId":324790,"journal":{"name":"Proceedings of the 9th ACM Cyber-Physical System Security Workshop","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122500329","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: 0

Data Security & Privacy Protection in IoT MGC Systems 物联网MGC系统中的数据安全和隐私保护

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2023-07-10 DOI: 10.1145/3592538.3607805

R. Deng

引用次数: 0

ICSML: Industrial Control Systems ML Framework for native inference using IEC 61131-3 code 使用IEC 61131-3代码进行本地推理的工业控制系统ML框架

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 2022-02-21 DOI: 10.1145/3592538.3594272

Constantine Doumanidis, Prashant Hari Narayan Rajput, M. Maniatakos

{"title":"ICSML: Industrial Control Systems ML Framework for native inference using IEC 61131-3 code","authors":"Constantine Doumanidis, Prashant Hari Narayan Rajput, M. Maniatakos","doi":"10.1145/3592538.3594272","DOIUrl":"https://doi.org/10.1145/3592538.3594272","url":null,"abstract":"Industrial Control Systems (ICS) have played a catalytic role in enabling the 4th Industrial Revolution. ICS devices like Programmable Logic Controllers (PLCs), automate, monitor, and control critical processes in industrial, energy, and commercial environments. The convergence of traditional Operational Technology (OT) with Information Technology (IT) has opened a new and unique threat landscape. This has inspired defense research that focuses heavily on Machine Learning (ML) based anomaly detection methods that run on external IT hardware, which means an increase in costs and the further expansion of the threat landscape. To remove this requirement, we introduce the ICS machine learning inference framework (ICSML) which enables executing ML model inference natively on the PLC. ICSML is implemented in IEC 61131-3 code and provides several optimizations to bypass the limitations imposed by the domain-specific languages. Therefore, it works on every PLC without the need for vendor support. ICSML provides a complete set of components for creating full ML models similarly to established ML frameworks. We run a series of benchmarks studying memory and performance, and compare our solution to the TFLite inference framework. At the same time, we develop domain-specific model optimizations to improve the efficiency of ICSML. To demonstrate the abilities of ICSML, we evaluate a case study of a real defense for process-aware attacks targeting a desalination plant.","PeriodicalId":324790,"journal":{"name":"Proceedings of the 9th ACM Cyber-Physical System Security Workshop","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122252340","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: 0

Proceedings of the 9th ACM Cyber-Physical System Security Workshop 第九届ACM信息物理系统安全研讨会论文集

Proceedings of the 9th ACM Cyber-Physical System Security Workshop Pub Date : 1900-01-01 DOI: 10.1145/3592538

引用次数: 0