Abstract:Safety and security are essential for the admission and acceptance of automated and autonomous vehicles. Deep neural networks (DNNs) are widely used for perception and further components of the autonomous driving (AD) stack. However, they possess several limitations, including lack of generalization, efficiency, explainability, plausibility, and robustness. These insufficiencies can pose significant risks to autonomous driving systems. However, hazards, threats, and risks associated with DNN limitations in this domain have not been systematically studied so far. In this work, we propose a joint workflow for risk assessment combining the hazard analysis and risk assessment (HARA) following ISO 26262 and threat analysis and risk assessment (TARA) following the ISO/SAE 21434 to identify and analyze risks arising from inherent DNN limitations in AD perception.
| Comments: | Accepted for publication at the SECAI workshop at ESORICS 2025 |
| Subjects: | Cryptography and Security (cs.CR); Computers and Society (cs.CY); Machine Learning (cs.LG) |
| Cite as: | arXiv:2604.20895 [cs.CR] |
| (or arXiv:2604.20895v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2604.20895 arXiv-issued DOI via DataCite (pending registration) |
From: Svetlana Pavlitska [view email]
[v1]
Tue, 21 Apr 2026 09:35:28 UTC (106 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。