mlsanityData to 14 Oct 2026

Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems

arXiv 2510.21254 ↗First posted 24 Oct 2025cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

The operational capabilities and application domains of AI-enabled autonomous systems have expanded significantly in recent years due to advances in robotics and machine learning (ML). Demonstrating the safety of autonomous systems rigorously is critical for their responsible adoption but it is challenging as it requires robust methodologies that can handle novel and uncertain situations throughout the system lifecycle, including detecting out-of-distribution (OoD) data. Thus, OOD detection is receiving increased attention from the research, development and safety engineering communities. This comprehensive review analyses OOD detection techniques within the context of safety assurance for autonomous systems, in particular in safety-critical domains. We begin by defining the relevant concepts, investigating what causes OOD and exploring the factors which make the safety assurance of autonomous systems and OOD detection challenging. Our review identifies a range of techniques which can be used throughout the ML development lifecycle and we suggest areas within the lifecycle in which they may be used to support safety assurance arguments. We discuss a number of caveats that system and safety engineers must be aware of when integrating OOD detection into system lifecycles. We conclude by outlining the challenges and future work necessary for the safe development and operation of autonomous systems across a range of domains and applications.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 93 of its 161 references that are in the map. First posted on arXiv 24 Oct 2025.

Builds on

93 of 161 references.

References · 93

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
38 more
  1. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  3. 2015Towards Open Set Deep Networkscited by 538
  4. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  5. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  6. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  7. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  8. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  9. 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
  10. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  11. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 405
  12. 2018Recent Advances in Open Set Recognition: A Surveycited by 310
  13. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  14. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  15. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  16. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  17. 2018Learning Confidence for Out-of-Distribution Detection in Neural Networkscited by 245
  18. 2017A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencodercited by 209
  19. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  20. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  21. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 148
  22. 2025Diffusion-Based Planning for Autonomous Driving with Flexible Guidancecited by 141
  23. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  24. 2020DROCC: Deep Robust One-Class Classificationcited by 121
  25. 2023The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systemscited by 88
  26. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  27. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  28. 2021The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuningcited by 75
  29. 2018Improving Reconstruction Autoencoder Out-of-distribution Detection with Mahalanobis Distancecited by 74
  30. 2024Real-Time Anomaly Detection and Reactive Planning with Large Language Modelscited by 68
  31. 2020Real-time Out-of-distribution Detection in Learning-Enabled Cyber-Physical Systemscited by 46
  32. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  33. 2021Guidance on the Assurance of Machine Learning in Autonomous Systems (AMLAS)cited by 42
  34. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 39
  35. 2019Robust Anomaly Detection in Images using Adversarial Autoencoderscited by 38
  36. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  37. 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
  38. 2022A System-Level View on Out-of-Distribution Data in Roboticscited by 33

50 most cited of 93 All 93 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Controlcited by 3
  2. 2026AI Assurance in UK Defence: Challenges in Operationalising JSP 936cited by 0