Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Conference proceeding
Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack
2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, pp 4389-4400
01 Jan 2023
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
In autonomous driving (AD), accurate perception is indispensable to achieving safe and secure driving. Due to its safety-criticality, the security of AD perception has been widely studied. Among different attacks on AD perception, the physical adversarial object evasion attacks are especially severe. However, we find that all existing literature only evaluates their attack effect at the targeted AI component level but not at the system level, i.e., with the entire system semantics and context such as the full AD pipeline. Thereby, this raises a critical research question: can these existing researches effectively achieve system-level attack effects (e.g., traffic rule violations) in the real-world AD context? In this work, we conduct the first measurement study on whether and how effectively the existing designs can lead to system-level effects, especially for the STOP sign-evasion attacks due to their popularity and severity. Our evaluation results show that all the representative prior works cannot achieve any system-level effects. We observe two design limitations in the prior works: 1) physical model-inconsistent object size distribution in pixel sampling and 2) lack of vehicle plant model and AD system model consideration. Then, we propose SysAdv, a novel system-driven attack design in the AD context and our evaluation results show that the system-level effects can be significantly improved, i.e., the violation rate increases by around 70%.
Metrics
Details
- Title
- Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack
- Creators
- Ningfei Wang - University of California, IrvineYunpeng Luo - University of California, IrvineTakami Sato - University of California, IrvineKaidi Xu - Drexel UniversityQi Alfred Chen - University of California, Irvine
- Publication Details
- 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, pp 4389-4400
- Series
- IEEE International Conference on Computer Vision
- Publisher
- IEEE
- Number of pages
- 12
- Grant note
- CNS-1932464; CNS-1929771; CNS-2145493 / NSF; National Science Foundation (NSF)
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:001159644304060
- Scopus ID
- 2-s2.0-85177434918
- Other Identifier
- 991021871341304721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Theory & Methods
- Imaging Science & Photographic Technology