mlsanityData to 7 Oct 2026

Maximum Resilience of Artificial Neural Networks

arXiv 1705.01040 ↗First posted 28 Apr 2017cs.LG cs.AI cs.LOcited by 97

Not on the map. Why?

Abstract (arXiv)

The deployment of Artificial Neural Networks (ANNs) in safety-critical applications poses a number of new verification and certification challenges. In particular, for ANN-enabled self-driving vehicles it is important to establish properties about the resilience of ANNs to noisy or even maliciously manipulated sensory input. We are addressing these challenges by defining resilience properties of ANN-based classifiers as the maximal amount of input or sensor perturbation which is still tolerated. This problem of computing maximal perturbation bounds for ANNs is then reduced to solving mixed integer optimization problems (MIP). A number of MIP encoding heuristics are developed for drastically reducing MIP-solver runtimes, and using parallelization of MIP-solvers results in an almost linear speed-up in the number (up to a certain limit) of computing cores in our experiments. We demonstrate the effectiveness and scalability of our approach by means of computing maximal resilience bounds for a number of ANN benchmark sets ranging from typical image recognition scenarios to the autonomous maneuvering of robots.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 27; 2023: 17; 2024: 14; 2025: 13; 2026: 3.

97 papers.

Sort:

By area:

  1. 2021Orthogonalizing Convolutional Layers with the Cayley Transformcited by 105
  2. 2022Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learningcited by 58
  3. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
  4. 2021Learning a Large Neighborhood Search Algorithm for Mixed Integer Programscited by 41
  5. 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 41
  6. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 40
  7. 2021Partition-based formulations for mixed-integer optimization of trained ReLU neural networkscited by 39
  8. 2022How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspectivecited by 39
  9. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  10. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  11. 2021A Review of Formal Methods applied to Machine Learningcited by 33
  12. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
38 more
  1. 2022Open- and Closed-Loop Neural Network Verification using Polynomial Zonotopescited by 24
  2. 2021Scaling Up Exact Neural Network Compression by ReLU Stabilitycited by 19
  3. 2021BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networkscited by 17
  4. 2021Provably Robust Detection of Out-of-distribution Data (almost) for freecited by 17
  5. 2022Maximizing information from chemical engineering data sets: Applications to machine learningcited by 17
  6. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  7. 2024Compact Proofs of Model Performance via Mechanistic Interpretabilitycited by 17
  8. 2022Neur2SP: Neural Two-Stage Stochastic Programmingcited by 16
  9. 2021Towards Evaluating and Training Verifiably Robust Neural Networkscited by 15
  10. 2022Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encodingcited by 15
  11. 2022A Unified View of SDP-based Neural Network Verification through Completely Positive Programmingcited by 12
  12. 2022QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networkscited by 12
  13. 2023POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systemscited by 12
  14. 2022UniCR: Universally Approximated Certified Robustness via Randomized Smoothingcited by 10
  15. 2023Learning To Dive In Branch And Boundcited by 10
  16. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  17. 2024Optimization Over Trained Neural Networks: Taking a Relaxing Walkcited by 10
  18. 2024Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifierscited by 10
  19. 2022MultiGuard: Provably Robust Multi-label Classification against Adversarial Examplescited by 9
  20. 2025Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verificationcited by 9
  21. 2021DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splittingcited by 8
  22. 2021Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networkscited by 8
  23. 2021Modeling Design and Control Problems Involving Neural Network Surrogatescited by 8
  24. 2023Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regionscited by 8
  25. 2021Recent Advances in Large Margin Learningcited by 7
  26. 2022Piecewise Linear Neural Networks and Deep Learningcited by 7
  27. 2022Invariance-Aware Randomized Smoothing Certificatescited by 7
  28. 2022Verified Probabilistic Policies for Deep Reinforcement Learningcited by 6
  29. 2022Certified Adversarial Robustness via Anisotropic Randomized Smoothingcited by 6
  30. 2023What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systemscited by 6
  31. 2023Computational Tradeoffs of Optimization-Based Bound Tightening in ReLU Networkscited by 6
  32. 2024Certification of Speaker Recognition Models to Additive Perturbationscited by 6
  33. 2021Fast Training of Provably Robust Neural Networks by SinglePropcited by 5
  34. 2021Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracycited by 5
  35. 2022Are Transformers More Robust? Towards Exact Robustness Verification for Transformerscited by 5
  36. 2022BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmeticcited by 5
  37. 2022Probabilistic Verification of ReLU Neural Networks via Characteristic Functionscited by 5
  38. 2023A Certified Radius-Guided Attack Framework to Image Segmentation Modelscited by 5

50 most cited of 97 All 97 (JSON)