Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception

Computer Science > Cryptography and Security [Submitted on 21 Apr 2026] Towards a Systematic Risk Assessment of Deep Neural Network Limitations in Autonomous Driving Perception Svetlana Pavlitska, Christopher Gerking, J. Marius Zöllner 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 Focus to learn more Submission history From: Svetlana Pavlitska [view email] [v1] Tue, 21 Apr 2026 09:35:28 UTC (106 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CY cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)