mlsanityData to 7 Oct 2026

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

arXiv 2406.00699 ↗First posted 2 Jun 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

The robustness of convolutional neural networks (CNNs) is vital to modern AI-driven systems. It can be quantified by formal verification by providing a certified lower bound, within which any perturbation does not alter the original input's classification result. It is challenging due to nonlinear components, such as MaxPool. At present, many verification methods are sound but risk losing some precision to enhance efficiency and scalability, and thus, a certified lower bound is a crucial criterion for evaluating the performance of verification tools. In this paper, we present MaxLin, a robustness verifier for MaxPool-based CNNs with tight linear approximation. By tightening the linear approximation of the MaxPool function, we can certify larger certified lower bounds of CNNs. We evaluate MaxLin with open-sourced benchmarks, including LeNet and networks trained on the MNIST, CIFAR-10, and Tiny ImageNet datasets. The results show that MaxLin outperforms state-of-the-art tools with up to 110.60% improvement regarding the certified lower bound and 5.13 × speedup for the same neural networks. Our code is available at https://github.com/xiaoyuanpigo/maxlin.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 2 Jun 2024.

Builds on

36 of 52 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2022A ConvNet for the 2020scited by 3,545
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2016Universal adversarial perturbationscited by 774
  11. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  12. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
24 more
  1. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  2. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  3. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  4. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  5. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  6. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 183
  7. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 102
  8. 2020SoK: Certified Robustness for Deep Neural Networkscited by 100
  9. 2022Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Boundcited by 92
  10. 2021PRIMA: General and Precise Neural Network Certification via Scalable Convex Hull Approximationscited by 77
  11. 2020Opportunities and Challenges in Deep Learning Adversarial Robustness: A Surveycited by 71
  12. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  13. 2016Achieving Human Parity in Conversational Speech Recognitioncited by 63
  14. 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
  15. 2020The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verificationcited by 50
  16. 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 41
  17. 2019Fastened CROWN: Tightened Neural Network Robustness Certificatescited by 39
  18. 2022The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Resultscited by 39
  19. 2019POPQORN: Quantifying Robustness of Recurrent Neural Networkscited by 36
  20. 2018Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attackscited by 31
  21. 2020Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificatescited by 17
  22. 2021Robustness Certification for Point Cloud Modelscited by 16
  23. 2022Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networkscited by 8
  24. 2022Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zonecited by 1

Built on by

Not cited yet.