# Deep Learning Safety Concerns in Automated Driving Perception

arXiv: https://arxiv.org/abs/2309.03774 · HTML: https://mlsanity.com/paper/2309.03774/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 60 references that are in the map.
- First posted on arXiv 7 Sep 2023.

## Builds on (most cited first, 30 of 33)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks](https://mlsanity.com/paper/2103.14749/) (2021)
- [Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem](https://mlsanity.com/paper/1812.05720/) (2018)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [A Fourier Perspective on Model Robustness in Computer Vision](https://mlsanity.com/paper/1906.08988/) (2019)
- [Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer](https://mlsanity.com/paper/2207.14024/) (2022)
- [Improving the Robustness of Deep Neural Networks via Stability Training](https://mlsanity.com/paper/1604.04326/) (2016)
- [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017)
- [Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time](https://mlsanity.com/paper/2211.14238/) (2022)
- [A Survey on Long-Tailed Visual Recognition](https://mlsanity.com/paper/2205.13775/) (2022)
- [Learning to Evaluate Perception Models Using Planner-Centric Metrics](https://mlsanity.com/paper/2004.08745/) (2020)
- [Evaluation Gaps in Machine Learning Practice](https://mlsanity.com/paper/2205.05256/) (2022)
- [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)
- [Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses](https://mlsanity.com/paper/2104.01789/) (2021)
- [Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches](https://mlsanity.com/paper/2102.05897/) (2021)
- [From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible ML](https://mlsanity.com/paper/2210.03535/) (2022)
- [Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices](https://mlsanity.com/paper/1909.06349/) (2019)
- [Meta Adversarial Training against Universal Patches](https://mlsanity.com/paper/2101.11453/) (2021)
- [Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining](https://mlsanity.com/paper/2210.08375/) (2022)
- [Identification of Systematic Errors of Image Classifiers on Rare Subgroups](https://mlsanity.com/paper/2303.05072/) (2023)
- [Visual Concepts and Compositional Voting](https://mlsanity.com/paper/1711.04451/) (2017)
- [Finding Label and Model Errors in Perception Data With Learned Observation Assertions](https://mlsanity.com/paper/2201.05797/) (2022)
- [Strategy to Increase the Safety of a DNN-based Perception for HAD Systems](https://mlsanity.com/paper/2002.08935/) (2020)

## Built on by (most cited first, 10 of 10)

- [Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection](https://mlsanity.com/paper/2506.17633/) (2025)
- [BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detection](https://mlsanity.com/paper/2403.18373/) (2024)
- [Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack](https://mlsanity.com/paper/2509.23871/) (2025)
- [Estimating the Robustness Radius for Randomized Smoothing with 100× Sample Efficiency](https://mlsanity.com/paper/2404.17371/) (2024)
- [A Flow-based Credibility Metric for Safety-critical Pedestrian Detection](https://mlsanity.com/paper/2402.07642/) (2024)
- [Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case](https://mlsanity.com/paper/2503.03548/) (2025)
- [A Systematic Literature Review on Safety of the Intended Functionality for Automated Driving Systems](https://mlsanity.com/paper/2503.02498/) (2025)
- [HiPreNets: High-Precision Neural Networks through Progressive Training](https://mlsanity.com/paper/2506.15064/) (2025)
- [Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Framework](https://mlsanity.com/paper/2509.05000/) (2025)
- [General Hazard Detection](https://mlsanity.com/paper/2605.23304/) (2026)

## Abstract (arXiv)

Recent advances in the field of deep learning and impressive performance of deep neural networks (DNNs) for perception have resulted in an increased demand for their use in automated driving (AD) systems. The safety of such systems is of utmost importance and thus requires to consider the unique properties of DNNs. In order to achieve safety of AD systems with DNN-based perception components in a systematic and comprehensive approach, so-called safety concerns have been introduced as a suitable structuring element. On the one hand, the concept of safety concerns is -- by design -- well aligned to existing standards relevant for safety of AD systems such as ISO 21448 (SOTIF). On the other hand, it has already inspired several academic publications and upcoming standards on AI safety such as ISO PAS 8800. While the concept of safety concerns has been previously introduced, this paper extends and refines it, leveraging feedback from various domain and safety experts in the field. In particular, this paper introduces an additional categorization for a better understanding as well as enabling cross-functional teams to jointly address the concerns.