mlsanityData to 7 Oct 2026

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

arXiv 2301.11342 ↗First posted 26 Jan 2023cs.LG math.OCcited by 3

Not on the map. Why?

Abstract (arXiv)

Counterexample-guided repair aims at creating neural networks with mathematical safety guarantees, facilitating the application of neural networks in safety-critical domains. However, whether counterexample-guided repair is guaranteed to terminate remains an open question. We approach this question by showing that counterexample-guided repair can be viewed as a robust optimisation algorithm. While termination guarantees for neural network repair itself remain beyond our reach, we prove termination for more restrained machine learning models and disprove termination in a general setting. We empirically study the practical implications of our theoretical results, demonstrating the suitability of common verifiers and falsifiers for repair despite a disadvantageous theoretical result. Additionally, we use our theoretical insights to devise a novel algorithm for repairing linear regression models based on quadratic programming, surpassing existing approaches.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 44 of its 89 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

44 of 89 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2021Convex optimizationcited by 2,479
  9. 2016Adversarial examples in the physical worldcited by 1,762
  10. 2016End to End Learning for Self-Driving Carscited by 1,000
  11. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  12. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
32 more
  1. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  2. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  3. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  4. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  5. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  6. 2018Certified Defenses against Adversarial Examplescited by 305
  7. 2017Parseval Networks: Improving Robustness to Adversarial Examplescited by 288
  8. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  9. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  10. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  11. 2017The Case for Learned Index Structurescited by 188
  12. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  13. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 183
  14. 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
  15. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  16. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
  17. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  18. 2022Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Boundcited by 92
  19. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  20. 2018Deep Neural Network Compression for Aircraft Collision Avoidance Systemscited by 58
  21. 2021Improved Branch and Bound for Neural Network Verification via Lagrangian Decompositioncited by 44
  22. 2021Provable Repair of Deep Neural Networkscited by 39
  23. 2020Counterexample-Guided Learning of Monotonic Neural Networkscited by 34
  24. 2019Guaranteeing Safety for Neural Network-Based Aircraft Collision Avoidance Systemscited by 26
  25. 2020Global Optimization of Objective Functions Represented by ReLU Networkscited by 24
  26. 2021Boosting the Certified Robustness of L-infinity Distance Netscited by 24
  27. 2020Towards Repairing Neural Networks Correctlycited by 13
  28. 2013Performance Bounds for the Scenario Approach and an Extension to a Class of Non-convex Programscited by 9
  29. 2019Verifying Aircraft Collision Avoidance Neural Networks Through Linear Approximations of Safe Regionscited by 8
  30. 2021SpecRepair: Counter-Example Guided Safety Repair of Deep Neural Networkscited by 6
  31. 2019A Counterexample-guided Approach to Finding Numerical Invariantscited by 3
  32. 2014Are There Good Mistakes? A Theoretical Analysis of CEGIScited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Criticscited by 1
  2. 2024AI-Powered CPS-Enabled Vulnerable-User-Aware Urban Transportation Digital Twin: Methods and Applicationscited by 1
  3. 2026Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcutscited by 0