mlsanityData to 14 Oct 2026

Deep Learning Safety Concerns in Automated Driving Perception

arXiv 2309.03774 ↗First posted 7 Sep 2023cs.LG cs.CV cs.SYcited by 10

Not on the map. Why?

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.

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

33 of 60 references.

References · 33

  1. 2017On Calibration of Modern Neural Networkscited by 4,960
  2. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,515
  5. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
  6. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  7. 2020Underspecification Presents Challenges for Credibility in Modern Machine Learningcited by 496
  8. 2021Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarkscited by 395
  9. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  10. 2021Unsolved Problems in ML Safetycited by 292
  11. 2019A Fourier Perspective on Model Robustness in Computer Visioncited by 288
  12. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 212
21 more
  1. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  2. 2017Universal Adversarial Perturbations Against Semantic Image Segmentationcited by 92
  3. 2022Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Timecited by 90
  4. 2022A Survey on Long-Tailed Visual Recognitioncited by 75
  5. 2020Learning to Evaluate Perception Models Using Planner-Centric Metricscited by 49
  6. 2022Evaluation Gaps in Machine Learning Practicecited by 49
  7. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  8. 2020Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Taskscited by 31
  9. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 30
  10. 2021Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approachescited by 27
  11. 2022From plane crashes to algorithmic harm: applicability of safety engineering frameworks for responsible MLcited by 27
  12. 2019Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slicescited by 23
  13. 2021Meta Adversarial Training against Universal Patchescited by 19
  14. 2022Improving the Intra-class Long-tail in 3D Detection via Rare Example Miningcited by 19
  15. 2023Identification of Systematic Errors of Image Classifiers on Rare Subgroupscited by 17
  16. 2017Visual Concepts and Compositional Votingcited by 6
  17. 2022Finding Label and Model Errors in Perception Data With Learned Observation Assertionscited by 6
  18. 2020Strategy to Increase the Safety of a DNN-based Perception for HAD Systemscited by 5
  19. 2021Thinking Beyond Distributions in Testing Machine Learned Modelscited by 5
  20. 2022Exploring Opportunities in Usable Hazard Analysis Processes for AI Engineeringcited by 3
  21. 2023System Theoretic View on Uncertaintiescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 1.

10 papers.

  1. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  2. 2024BAM: Box Abstraction Monitors for Real-time OoD Detection in Object Detectioncited by 5
  3. 2025Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attackcited by 5
  4. 2024Estimating the Robustness Radius for Randomized Smoothing with 100× Sample Efficiencycited by 4
  5. 2024A Flow-based Credibility Metric for Safety-critical Pedestrian Detectioncited by 2
  6. 2025Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Casecited by 1
  7. 2025A Systematic Literature Review on Safety of the Intended Functionality for Automated Driving Systemscited by 0
  8. 2025HiPreNets: High-Precision Neural Networks through Progressive Trainingcited by 0
  9. 2025Dual-Domain Perspective on Degradation-Aware Fusion: A VLM-Guided Robust Infrared and Visible Image Fusion Frameworkcited by 0
  10. 2026General Hazard Detectioncited by 0