Yuting Wu, Xin Lou, Pengfei Zhou, Rui Tan, Z. Kalbarczyk, Ravishankar K. Iyer
{"title":"Susceptibility of Autonomous Driving Agents to Learning-Based Action-Space Attacks","authors":"Yuting Wu, Xin Lou, Pengfei Zhou, Rui Tan, Z. Kalbarczyk, Ravishankar K. Iyer","doi":"10.1109/DSN-W58399.2023.00034","DOIUrl":"https://doi.org/10.1109/DSN-W58399.2023.00034","url":null,"abstract":"Intelligent vehicles with increasing complexity face cybersecurity threats. This paper studies action-space attacks on autonomous driving agents that make decisions using either a traditional modular processing pipeline or the recently proposed end-to-end driving model obtained via deep reinforcement learning (DRL). Such attacks alter the actuation signal and pose direct risks to the vehicle’s state. We formulate the attack construction as a DRL problem based on the input from either an extra camera or inertial measurement unit deployed. The attacks are designed to lurk until a safety-critical moment arises and cause a side collision upon activation. We analyze the behavioral differences between two driving agents when subjected to action-space attacks and demonstrate the superior resilience of the modular processing pipeline. We further investigate the performance and limitations of two enhancement methods, i.e., adversarial training through fine-tuning and progressive neural networks. The result offers valuable insights into vehicle safety from the viewpoints of both the assailant and the defender and informs the future design of autonomous driving systems.","PeriodicalId":422147,"journal":{"name":"2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128608966","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}
{"title":"An Automotive Cybersecurity Maturity Level Assessment Programme","authors":"P. Grümer, Pedro Brandao","doi":"10.1109/DSN-W58399.2023.00035","DOIUrl":"https://doi.org/10.1109/DSN-W58399.2023.00035","url":null,"abstract":"Cybersecurity will be key for the new and future vehicles that depend on the exchange of data with the infrastructure. These vehicles will bring countless new features and are potentially capable of autonomous driving. This paper analyses the automotive threats, standards and regulations. An explanation about the automotive future vision and cybersecurity dependency is given. The main presentation is a high-level model of a five-grade rating system responsible for evaluating the cybersecurity quality of the future vehicles, in order to establish a trustable and reliable environment. Based on the standards used for secure software development and security assessment we defined a procedure for the evaluation of security of the technological components of a car.","PeriodicalId":422147,"journal":{"name":"2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128730344","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}
Janek Groß, Michael Kläs, Lisa Jöckel, Pascal Gerber
{"title":"Timeseries-aware Uncertainty Wrappers for Uncertainty Quantification of Information-Fusion-Enhanced AI Models based on Machine Learning","authors":"Janek Groß, Michael Kläs, Lisa Jöckel, Pascal Gerber","doi":"10.1109/DSN-W58399.2023.00061","DOIUrl":"https://doi.org/10.1109/DSN-W58399.2023.00061","url":null,"abstract":"As the use of Artificial Intelligence (AI) components in cyber-physical systems is becoming more common, the need for reliable system architectures arises. While data-driven models excel at perception tasks, model outcomes are usually not dependable enough for safety-critical applications. In this work, we present a timeseries-aware uncertainty wrapper for dependable uncertainty estimates on timeseries data. The uncertainty wrapper is applied in combination with information fusion over successive model predictions in time. The application of the uncertainty wrapper is demonstrated with a traffic sign recognition use case. We show that it is possible to increase model accuracy through information fusion and additionally increase the quality of uncertainty estimates through timeseries-aware input quality features.","PeriodicalId":422147,"journal":{"name":"2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"21 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114133604","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}
F. Oberti, Ernesto Sánchez, A. Savino, Filippo Parisi, S. Carlo
{"title":"PSP Framework: A novel risk assessment method in compliance with ISO/SAE-21434","authors":"F. Oberti, Ernesto Sánchez, A. Savino, Filippo Parisi, S. Carlo","doi":"10.1109/DSN-W58399.2023.00031","DOIUrl":"https://doi.org/10.1109/DSN-W58399.2023.00031","url":null,"abstract":"As more cars connect to the internet and other devices, the automotive market has become a lucrative target for cyberattacks. This has made the industry more vulnerable to security threats. As a result, car manufacturers and governments are working together to reduce risks and prevent cyberattacks in the automotive sector. However, existing attack feasibility models derived from the information technology field may not always provide accurate assessments of the potential risks faced by Vehicle Electronic Control Units in different operating conditions and domains. To address this issue, This paper introduces the PUNCH Softronix and Politecnico di Torino (PSP) framework. This framework is designed to provide accurate assessments compatible with the attack feasibility models defined by the automotive product security standards. The PSP framework utilizes social sentiment analysis to evaluate the real threat risk levels.","PeriodicalId":422147,"journal":{"name":"2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116775303","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}
Tânia Esteves, Ricardo Macedo, Rui Oliveira, J. Paulo
{"title":"Diagnosing applications’ I/O behavior through system call observability","authors":"Tânia Esteves, Ricardo Macedo, Rui Oliveira, J. Paulo","doi":"10.1109/DSN-W58399.2023.00022","DOIUrl":"https://doi.org/10.1109/DSN-W58399.2023.00022","url":null,"abstract":"We present DIO, a generic tool for observing inefficient and erroneous I/O interactions between applications and in-kernel storage systems that lead to performance, dependability, and correctness issues. DIO facilitates the analysis and enables near real-time visualization of complex I/O patterns for data-intensive applications generating millions of storage requests. This is achieved by non-intrusively intercepting system calls, enriching collected data with relevant context, and providing timely analysis and visualization for traced events. We demonstrate its usefulness by analyzing two production-level applications. Results show that DIO enables diagnosing resource contention in multi-threaded I/O that leads to high tail latency and erroneous file accesses that cause data loss.","PeriodicalId":422147,"journal":{"name":"2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131939601","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}
{"title":"IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness","authors":"Xiaoyun Xu, Guilherme Perin, S. Picek","doi":"10.1109/DSN-W58399.2023.00041","DOIUrl":"https://doi.org/10.1109/DSN-W58399.2023.00041","url":null,"abstract":"This paper proposes a novel method, IB-RAR, which uses Information Bottleneck (IB) to strengthen adversarial robustness for both adversarial training and non-adversarial-trained methods. We first use the IB theory to build regularizers as learning objectives in the loss function. Then we filter out unnecessary features of intermediate representation according to their mutual information (MI) with labels, as the network trained with IB provides easily distinguishable MI for its features. Experimental results show that IB-RAR can be naturally combined with adversarial training and provides consistently better accuracy on new adversarial examples. The IB-RAR method improves the accuracy by an average of 2.66% against five adversarial attacks for ResNet-18, wide ResNet-28-10, and VGG-16, trained with three adversarial training benchmarks and the CFAR-10, CFAR-100, and Tiny ImageNet datasets. In addition, IB-RAR also provides good robustness for undefended methods, such as training with cross-entropy loss only. Finally, without adversarial training, the VGG-16 network trained using IB-RAR on the CFAR-10 dataset reaches an accuracy of 35.86% against PGD examples, while using all layers reaches 25.61% accuracy.","PeriodicalId":422147,"journal":{"name":"2023 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129346305","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}