mlsanityData to 14 Oct 2026

Is the Rush to Machine Learning Jeopardizing Safety? Results of a Survey

arXiv 2111.14324 ↗First posted 29 Nov 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine learning (ML) is finding its way into safety-critical systems (SCS). Current safety standards and practice were not designed to cope with ML techniques, and it is difficult to be confident that SCSs that contain ML components are safe. Our hypothesis was that there has been a rush to deploy ML techniques at the expense of a thorough examination as to whether the use of ML techniques introduces safety problems that we are not yet adequately able to detect and mitigate against. We thus conducted a targeted literature survey to determine the research effort that has been expended in applying ML to SCS compared with that spent on evaluating the safety of SCSs that deploy ML components. This paper presents the (surprising) results of the survey.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 147 references that are in the map. First posted on arXiv 29 Nov 2021.

Builds on

31 of 147 references.

References · 31

  1. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  2. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  3. 2018Certified Defenses against Adversarial Examplescited by 306
  4. 2018A Lyapunov-based Approach to Safe Reinforcement Learningcited by 297
  5. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 195
  6. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
  7. 2017Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learningcited by 90
  8. 2016Safe Exploration in Finite Markov Decision Processes with Gaussian Processescited by 75
  9. 2020Safe Reinforcement Learning via Curriculum Inductioncited by 74
  10. 2019Adaptive and Safe Bayesian Optimization in High Dimensions via One-Dimensional Subspacescited by 73
  11. 2020Safe Imitation Learning via Fast Bayesian Reward Inference from Preferencescited by 73
  12. 2018On Testing Machine Learning Programscited by 48
19 more
  1. 2018Penalizing side effects using stepwise relative reachabilitycited by 38
  2. 2020Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systemscited by 35
  3. 2020Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception Taskscited by 31
  4. 2020Towards Safe Policy Improvement for Non-Stationary MDPscited by 26
  5. 2020Fast OSCAR and OWL Regression via Safe Screening Rulescited by 25
  6. 2020Machine Learning for Reliability Engineering and Safety Applications: Review of Current Status and Future Opportunitiescited by 23
  7. 2020A Safety Framework for Critical Systems Utilising Deep Neural Networkscited by 19
  8. 2017Efficient, Safe, and Probably Approximately Complete Learning of Action Modelscited by 16
  9. 2015Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regretcited by 15
  10. 2019Multi-Robot Collision Avoidance under Uncertainty with Probabilistic Safety Barrier Certificatescited by 13
  11. 2019Towards a Framework to Manage Perceptual Uncertainty for Safe Automated Drivingcited by 12
  12. 2018Learning Safe Policies with Expert Guidancecited by 11
  13. 2020Safe Screening Rules for ℓ0-Regressioncited by 7
  14. 2018Dynamic Risk Assessment for Vehicles of Higher Automation Levels by Deep Learningcited by 5
  15. 2017Dynamic Safe Interruptibility for Decentralized Multi-Agent Reinforcement Learningcited by 4
  16. 2019A Machine-learning Based Ensemble Method For Anti-patterns Detectioncited by 4
  17. 2018A Learning Approach to Enhance Assurances for Real-Time Self-Adaptive Systemscited by 3
  18. 2020A Machine Learning Based Framework for Code Clone Validationcited by 3
  19. 2019Detecting Spiky Corruption in Markov Decision Processescited by 1

Built on by

Not cited yet.