mlsanityData to 7 Oct 2026

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

arXiv 2604.20895 ↗First posted 21 Apr 2026cs.CR cs.CY cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 30 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

14 of 30 references.

References · 14

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  4. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  5. 2017Adversarial Patchcited by 514
  6. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 92
  7. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  8. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  9. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  10. 2020Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Taskscited by 31
  11. 2020Strategy to Increase the Safety of a DNN-based Perception for HAD Systemscited by 5
  12. 2022Plausibility Verification For 3D Object Detectors Using Energy-Based Optimizationcited by 3
2 more
  1. 2021Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentationcited by 1
  2. 2025Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectorscited by 1

Built on by

Not cited yet.