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

arXiv:2604.20895v1 Announce Type: cross 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.

Towards Verified and Targeted Explanations through Formal Methods
Spatiotemporal-Aware Bit-Flip Injection on DNN-based Advanced Driver Assistance Systems (extended version)
Heterogeneous Self-Play for Realistic Highway Traffic Simulation
When Can We Trust Deep Neural Networks? Towards Reliable Industrial Deployment with an Interpretability Guide
RISC-V Functional Safety for Autonomous Automotive Systems: An Analytical Framework and Research Roadmap for ML-Assisted Certification
From Particles to Perils: SVGD-Based Hazardous Scenario Generation for Autonomous Driving Systems Testing

Source: arXiv cs.LG | 2026-04-24

Related