mlsanityData to 7 Oct 2026

DelBugV: Delta-Debugging Neural Network Verifiers

arXiv 2305.18558 ↗First posted 29 May 2023cs.LO cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are becoming a key component in diverse systems across the board. However, despite their success, they often err miserably; and this has triggered significant interest in formally verifying them. Unfortunately, DNN verifiers are intricate tools, and are themselves susceptible to soundness bugs. Due to the complexity of DNN verifiers, as well as the sizes of the DNNs being verified, debugging such errors is a daunting task. Here, we present a novel tool, named DelBugV, that uses automated delta debugging techniques on DNN verifiers. Given a malfunctioning DNN verifier and a correct verifier as a point of reference (or, in some cases, just a single, malfunctioning verifier), DelBugV can produce much simpler DNN verification instances that still trigger undesired behavior -- greatly facilitating the task of debugging the faulty verifier. Our tool is modular and extensible, and can easily be enhanced with additional network simplification methods and strategies. For evaluation purposes, we ran DelBugV on 4 DNN verification engines, which were observed to produce incorrect results at the 2021 neural network verification competition (VNN-COMP'21). We were able to simplify many of the verification queries that trigger these faulty behaviors, by as much as 99%. We regard our work as a step towards the ultimate goal of producing reliable and trustworthy DNN-based software.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 41 of its 65 references that are in the map. First posted on arXiv 29 May 2023.

Builds on

41 of 65 references.

References · 41

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  3. 2019Multi-Task Deep Neural Networks for Natural Language Understandingcited by 349
  4. 2016Safety Verification of Deep Neural Networkscited by 262
  5. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  6. 2019Algorithms for Verifying Deep Neural Networkscited by 221
  7. 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
  8. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  9. 2017Output Reachable Set Estimation and Verification for Multi-Layer Neural Networkscited by 79
  10. 2021PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximationscited by 77
  11. 2015A Primer on Neural Network Models for Natural Language Processingcited by 75
  12. 2020Verification of Deep Convolutional Neural Networks Using ImageStarscited by 75
29 more
  1. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  2. 2021Introduction to Neural Network Verificationcited by 63
  3. 2023First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)cited by 58
  4. 2019Quantitative Verification of Neural Networks And its Security Applicationscited by 56
  5. 2017DeepSF: deep convolutional neural network for mapping protein sequences to foldscited by 46
  6. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  7. 2019Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustnesscited by 40
  8. 2020Parallelization Techniques for Verifying Neural Networkscited by 36
  9. 2020Exploiting Verified Neural Networks via Floating Point Numerical Errorcited by 35
  10. 2020Abstraction based Output Range Analysis for Neural Networkscited by 34
  11. 2021Towards Scalable Verification of Deep Reinforcement Learningcited by 33
  12. 2019GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processingcited by 31
  13. 2020DeepAbstract: Neural Network Abstraction for Accelerating Verificationcited by 31
  14. 2020Verifying Recurrent Neural Networks using Invariant Inferencecited by 25
  15. 2020Global Optimization of Objective Functions Represented by ReLU Networkscited by 24
  16. 2021NNrepair: Constraint-based Repair of Neural Network Classifierscited by 24
  17. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  18. 2022Efficient Neural Network Analysis with Sum-of-Infeasibilitiescited by 24
  19. 2017DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networkscited by 20
  20. 2021Pruning and Slicing Neural Networks using Formal Verificationcited by 20
  21. 2021Neural Network Repair with Reachability Analysiscited by 19
  22. 2022Verification-Aided Deep Ensemble Selectioncited by 18
  23. 2015Deep Image: Scaling up Image Recognitioncited by 16
  24. 2019Machine learning for protein folding and dynamicscited by 15
  25. 2020Towards Repairing Neural Networks Correctlycited by 13
  26. 2022veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection Systemcited by 12
  27. 2021Bisimulations for Neural Network Reductioncited by 6
  28. 2021Static analysis of ReLU neural networks with tropical polyhedracited by 5
  29. 2020CounterExample Guided Neural Synthesiscited by 4

Built on by

Cited by year

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

3 papers.

  1. 2024SoundnessBench: A Soundness Benchmark for Neural Network Verifierscited by 5
  2. 2025Abstraction-Based Proof Production in Formal Verification of Neural Networkscited by 5
  3. 2024Towards Formal Verification of Deep Neural Networks for Object Detectioncited by 4