mlsanityData to 7 Oct 2026

Scaling Polyhedral Neural Network Verification on GPUs

arXiv 2007.10868 ↗First posted 20 Jul 2020cs.LG stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

Certifying the robustness of neural networks against adversarial attacks is essential to their reliable adoption in safety-critical systems such as autonomous driving and medical diagnosis. Unfortunately, state-of-the-art verifiers either do not scale to bigger networks or are too imprecise to prove robustness, limiting their practical adoption. In this work, we introduce GPUPoly, a scalable verifier that can prove the robustness of significantly larger deep neural networks than previously possible. The key technical insight behind GPUPoly is the design of custom, sound polyhedra algorithms for neural network verification on a GPU. Our algorithms leverage the available GPU parallelism and inherent sparsity of the underlying verification task. GPUPoly scales to large networks: for example, it can prove the robustness of a 1M neuron, 34-layer deep residual network in approximately 34.5 ms. We believe GPUPoly is a promising step towards practical verification of real-world neural networks.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 11; 2023: 9; 2024: 8; 2025: 5; 2026: 4.

43 papers.

Sort:

  1. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
  2. 2021PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximationscited by 77
  3. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  4. 2023First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)cited by 58
  5. 2024Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planescited by 33
  6. 2022Efficient Neural Network Analysis with Sum-of-Infeasibilitiescited by 24
  7. 2023A DPLL(T) Framework for Verifying Deep Neural Networkscited by 23
  8. 2022IBP Regularization for Verified Adversarial Robustness via Branch-and-Boundcited by 21
  9. 2022Scalable Verification of GNN-based Job Schedulerscited by 18
  10. 2021Learning Security Classifiers with Verified Global Robustness Propertiescited by 14
  11. 2022Provable Defense Against Geometric Transformationscited by 14
  12. 2023Incremental Verification of Neural Networkscited by 14
31 more
  1. 2024Harnessing Neuron Stability to Improve DNN Verificationcited by 13
  2. 2021On the Paradox of Certified Trainingcited by 12
  3. 2022Stability Verification of Neural Network Controllers using Mixed-Integer Programmingcited by 10
  4. 2026Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guaranteescited by 10
  5. 2022CAISAR: A platform for Characterizing Artificial Intelligence Safety and Robustnesscited by 9
  6. 2022Improved techniques for deterministic l2 robustnesscited by 9
  7. 2025Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verificationcited by 9
  8. 2024Set-Based Training for Neural Network Verificationcited by 6
  9. 2021Self-Correcting Neural Networks For Safe Classificationcited by 4
  10. 2022Boosting Robustness Verification of Semantic Feature Neighborhoodscited by 4
  11. 2022Optimized Symbolic Interval Propagation for Neural Network Verificationcited by 4
  12. 2023Efficient MILP Decomposition in Quantum Computing for ReLU Network Robustnesscited by 4
  13. 2024Revisiting Differential Verification: Equivalence Verification with Confidencecited by 4
  14. 2022Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networkscited by 3
  15. 2023Interpreting Robustness Proofs of Deep Neural Networkscited by 3
  16. 2024VerifIoU -- Robustness of Object Detection to Perturbationscited by 3
  17. 2024Boosting Few-Pixel Robustness Verification via Covering Verification Designscited by 2
  18. 2025Verification of Bit-Flip Attacks against Quantized Neural Networkscited by 2
  19. 2021Abstract Interpretation of Fixpoint Iterators with Applications to Neural Networkscited by 1
  20. 2023Expediting Neural Network Verification via Network Reductioncited by 1
  21. 2024Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networkscited by 1
  22. 2025Mini-Batch Robustness Verification of Deep Neural Networkscited by 1
  23. 2025Tight Robustness Certification Through the Convex Hull of ℓ0 Attackscited by 1
  24. 2023CGDTest: A Constrained Gradient Descent Algorithm for Testing Neural Networkscited by 0
  25. 2023Verification of Neural Networks Local Differential Classification Privacycited by 0
  26. 2024Inferring Properties of Graph Neural Networkscited by 0
  27. 2023STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformerscited by 0
  28. 2025Evaluation and Verification of Physics-Informed Neural Models of the Grad-Shafranov Equationcited by 0
  29. 2026Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networkscited by 0
  30. 2026Scaling Neural Network Verification with Tensor Parallelism and Fully Sharded Data Parallelismcited by 0
  31. 2026Certified Training for Convolutional Perturbationscited by 0