mlsanityData to 7 Oct 2026

What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems

arXiv 2307.11784 ↗First posted 20 Jul 2023cs.LG cs.AI cs.SEcited by 6

Not on the map. Why?

Abstract (arXiv)

Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving safety guarantees is one of the most prominent. In this paper, we first discuss the engineering and research challenges associated with the design and verification of such systems. Then, based on the observation that existing works cannot actually achieve provable guarantees, we promote a two-step verification method for the ultimate achievement of provable statistical guarantees.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 42 of its 76 references that are in the map. First posted on arXiv 20 Jul 2023.

Builds on

42 of 76 references.

References · 42

  1. 2018Reconciling modern machine learning practice and the bias-variance trade-offcited by 919
  2. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  3. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  4. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  5. 2019Deep Double Descent: Where Bigger Models and More Data Hurtcited by 667
  6. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  7. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  8. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 307
  9. 2016Safety Verification of Deep Neural Networkscited by 262
  10. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  11. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  12. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
30 more
  1. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
  2. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  3. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  4. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  5. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  6. 2023A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validationcited by 91
  7. 2017Verifying Properties of Binarized Deep Neural Networkscited by 77
  8. 2018A Statistical Approach to Assessing Neural Network Robustnesscited by 54
  9. 2016Towards Verified Artificial Intelligencecited by 36
  10. 2019Outside the Box: Abstraction-Based Monitoring of Neural Networkscited by 36
  11. 2018Runtime Monitoring Neuron Activation Patternscited by 34
  12. 2018A Game-Based Approximate Verification of Deep Neural Networks with Provable Guaranteescited by 33
  13. 2019Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verificationcited by 28
  14. 2022SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretabilitycited by 28
  15. 2023Sources of Uncertainty in Supervised Machine Learning -- A Statisticians' Viewcited by 27
  16. 2021Distribution-Aware Testing of Neural Networks Using Generative Modelscited by 22
  17. 2020A Safety Framework for Critical Systems Utilising Deep Neural Networkscited by 19
  18. 2020Into the Unknown: Active Monitoring of Neural Networkscited by 19
  19. 2022PRoA: A Probabilistic Robustness Assessment against Functional Perturbationscited by 19
  20. 2019Statistically Robust Neural Network Classificationcited by 16
  21. 2021Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurancecited by 16
  22. 2019Coverage Guided Testing for Recurrent Neural Networkscited by 15
  23. 2021Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profilescited by 11
  24. 2021PerceMon: Online Monitoring for Perception Systemscited by 11
  25. 2020Provably-Robust Runtime Monitoring of Neuron Activation Patternscited by 9
  26. 2022Hierarchical Distribution-Aware Testing of Deep Learningcited by 8
  27. 2021Distribution Awareness for AI System Testingcited by 6
  28. 2020Manifold-based Test Generation for Image Classifierscited by 3
  29. 2022Prioritizing Corners in OoD Detectors via Symbolic String Manipulationcited by 3
  30. 2020From Requirements to Autonomous Flight: An Overview of the Monitoring ICAROUS Projectcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 5.

6 papers.

  1. 2025Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignmentcited by 7
  2. 2025Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guidecited by 6
  3. 2025Ensuring Reliability via Hyperparameter Selection: Review and Advancescited by 3
  4. 2024Runtime Monitoring and Fault Detection for Neural Network-Controlled Systemscited by 0
  5. 2025Enhancing Performance of Explainable AI Models with Constrained Concept Refinementcited by 0
  6. 2025Towards provable probabilistic safety for scalable embodied AI systemscited by 0