mlsanityData to 7 Oct 2026

Incremental Verification of Neural Networks

arXiv 2304.01874 ↗First posted 4 Apr 2023cs.LG cs.PL cs.SEcited by 14

Not on the map. Why?

Abstract (arXiv)

Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e.g., robustness, fairness) on an infinite set of inputs or not. Despite the tremendous progress to improve the scalability of complete verifiers over the years on individual DNNs, they are inherently inefficient when a deployed DNN is updated to improve its inference speed or accuracy. The inefficiency is because the expensive verifier needs to be run from scratch on the updated DNN. To improve efficiency, we propose a new, general framework for incremental and complete DNN verification based on the design of novel theory, data structure, and algorithms. Our contributions implemented in a tool named IVAN yield an overall geometric mean speedup of 2.4x for verifying challenging MNIST and CIFAR10 classifiers and a geometric mean speedup of 3.8x for the ACAS-XU classifiers over the state-of-the-art baselines.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 39 of its 77 references that are in the map. First posted on arXiv 4 Apr 2023.

Builds on

39 of 77 references.

References · 39

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  4. 2016End to End Learning for Self-Driving Carscited by 1,000
  5. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  6. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  7. 2020What is the State of Neural Network Pruning?cited by 578
  8. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  9. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  10. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  11. 2017Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?cited by 220
  12. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
27 more
  1. 2019Branch and Bound for Piecewise Linear Neural Network Verificationcited by 138
  2. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 124
  3. 2018Strong mixed-integer programming formulations for trained neural networkscited by 115
  4. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
  5. 2022Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Boundcited by 92
  6. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  7. 2021Introduction to Neural Network Verificationcited by 63
  8. 2018Deep Neural Network Compression for Aircraft Collision Avoidance Systemscited by 58
  9. 2020Robust Out-of-distribution Detection for Neural Networkscited by 57
  10. 2019Neural Network Branching for Neural Network Verificationcited by 45
  11. 2020Scaling Polyhedral Neural Network Verification on GPUscited by 43
  12. 2019Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustnesscited by 40
  13. 2021A Review of Formal Methods applied to Machine Learningcited by 33
  14. 2017Output Range Analysis for Deep Neural Networkscited by 30
  15. 2020ReluDiff: Differential Verification of Deep Neural Networkscited by 29
  16. 2020Attribute-Guided Adversarial Training for Robustness to Natural Perturbationscited by 23
  17. 2020NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximationcited by 22
  18. 2020Fast Geometric Projections for Local Robustness Certificationcited by 21
  19. 2019Computing Linear Restrictions of Neural Networkscited by 14
  20. 2022Provable Defense Against Geometric Transformationscited by 14
  21. 2021Sound and Complete Neural Network Repair with Minimality and Locality Guaranteescited by 12
  22. 2021Shared Certificates for Neural Network Verificationcited by 10
  23. 2020An efficient nonconvex reformulation of stagewise convex optimization problemscited by 7
  24. 2020Secure Medical Image Analysis with CrypTFlowcited by 6
  25. 2020Continuous Safety Verification of Neural Networkscited by 5
  26. 2021Demanded Abstract Interpretation (Extended Version)cited by 4
  27. 2022Boosting Robustness Verification of Semantic Feature Neighborhoodscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 7; 2026: 4.

14 papers.

Sort:

By area:

  1. 2023Incremental Randomized Smoothing Certificationcited by 12
  2. 2024Is The Watermarking Of LLM-Generated Code Robust?cited by 7
  3. 2025Faster Verified Explanations for Neural Networkscited by 4
  4. 2025Adaptive Branch-and-Bound Tree Exploration for Neural Network Verificationcited by 2
  5. 2025BEAVER: An Efficient Deterministic LLM Verifiercited by 2
  6. 2026Incremental Neural Network Verification via Learned Conflictscited by 2
  7. 2024ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNscited by 1
  8. 2025Mini-Batch Robustness Verification of Deep Neural Networkscited by 1
  9. 2025Support is All You Need for Certified VAE Trainingcited by 0
  10. 2025MUC-G4: Minimal Unsat Core-Guided Incremental Verification for Deep Neural Network Compressioncited by 0
  11. 2025Efficient Neural Network Verification via Order Leading Exploration of Branch-and-Bound Treescited by 0
  12. 2026Branch and Bound for Relational Verification of Neural Networkscited by 0
2 more
  1. 2026Uncovering the Limits of Proof Sharing for Neural Networkscited by 0
  2. 2026Exploring Solver-Level Warmstarting for Neural Network Verificationcited by 0