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

arXiv: https://arxiv.org/abs/2604.20895 · HTML: https://mlsanity.com/paper/2604.20895/

## Key facts

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

## Builds on (most cited first, 14 of 14)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Adversarial Sticker: A Stealthy Attack Method in the Physical World](https://mlsanity.com/paper/2104.06728/) (2021)
- [Anomaly Detection in Autonomous Driving: A Survey](https://mlsanity.com/paper/2204.07974/) (2022)
- [Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks](https://mlsanity.com/paper/2108.06179/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Tasks](https://mlsanity.com/paper/2001.08001/) (2020)
- [Strategy to Increase the Safety of a DNN-based Perception for HAD Systems](https://mlsanity.com/paper/2002.08935/) (2020)
- [Plausibility Verification For 3D Object Detectors Using Energy-Based Optimization](https://mlsanity.com/paper/2211.05233/) (2022)
- [Plants Don't Walk on the Street: Common-Sense Reasoning for Reliable Semantic Segmentation](https://mlsanity.com/paper/2104.09254/) (2021)
- [Fool the Stoplight: Realistic Adversarial Patch Attacks on Traffic Light Detectors](https://mlsanity.com/paper/2506.04823/) (2025)

## 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.