mlsanityData to 7 Oct 2026

An approach to reachability analysis for feed-forward ReLU neural networks

arXiv 1706.07351 ↗First posted 22 Jun 2017cs.AI cs.LG cs.LOcited by 126

Not on the map. Why?

Abstract (arXiv)

We study the reachability problem for systems implemented as feed-forward neural networks whose activation function is implemented via ReLU functions. We draw a correspondence between establishing whether some arbitrary output can ever be outputed by a neural system and linear problems characterising a neural system of interest. We present a methodology to solve cases of practical interest by means of a state-of-the-art linear programs solver. We evaluate the technique presented by discussing the experimental results obtained by analysing reachability properties for a number of benchmarks in the literature.

Key facts. Cited by 126 papers in the map (data through 7 Oct 2026). First posted on arXiv 22 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 30; 2023: 26; 2024: 16; 2025: 14; 2026: 10.

126 papers.

Sort:

By area:

  1. 2021Orthogonalizing Convolutional Layers with the Cayley Transformcited by 105
  2. 2021Certified Patch Robustness via Smoothed Vision Transformerscited by 44
  3. 2021Reachability Analysis of Neural Feedback Loopscited by 41
  4. 2022Adversarial Robustness of Deep Neural Networks: A Survey from a Formal Verification Perspectivecited by 41
  5. 2021Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Aheadcited by 40
  6. 2021Partition-based formulations for mixed-integer optimization of trained ReLU neural networkscited by 39
  7. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  8. 2021OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systemscited by 37
  9. 2021Multi-Label Classification Neural Networks with Hard Logical Constraintscited by 36
  10. 2022OMLT: Optimization & Machine Learning Toolkitcited by 34
  11. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  12. 2021Low Curvature Activations Reduce Overfitting in Adversarial Trainingcited by 29
38 more
  1. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  2. 2021ANCER: Anisotropic Certification via Sample-wise Volume Maximizationcited by 23
  3. 2023Expressive Losses for Verified Robustness via Convex Combinationscited by 23
  4. 2021Safe Control with Neural Network Dynamic Modelscited by 21
  5. 2021Pruning and Slicing Neural Networks using Formal Verificationcited by 20
  6. 2021Neural Network Repair with Reachability Analysiscited by 19
  7. 2023The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networkscited by 19
  8. 2022Verification-Aided Deep Ensemble Selectioncited by 18
  9. 2021BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networkscited by 17
  10. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  11. 2022Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encodingcited by 15
  12. 2024Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothingcited by 15
  13. 2021Learning Security Classifiers with Verified Global Robustness Propertiescited by 14
  14. 2021Neural Network Verification in Controlcited by 14
  15. 2021Minimal Multi-Layer Modifications of Deep Neural Networkscited by 14
  16. 2024Verification-Guided Shielding for Deep Reinforcement Learningcited by 13
  17. 2021Infinite Time Horizon Safety of Bayesian Neural Networkscited by 12
  18. 2022A Unified View of SDP-based Neural Network Verification through Completely Positive Programmingcited by 12
  19. 2022veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection Systemcited by 12
  20. 2023POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systemscited by 12
  21. 2022Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networkscited by 11
  22. 2023Verifying Generalization in Deep Learningcited by 11
  23. 2021Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllerscited by 10
  24. 2022CARE: Certifiably Robust Learning with Reasoning via Variational Inferencecited by 10
  25. 2023Efficient Error Certification for Physics-Informed Neural Networkscited by 10
  26. 2024A Survey on Verification and Validation, Testing and Evaluations of Neurosymbolic Artificial Intelligencecited by 10
  27. 2024Verifying message-passing neural networks via topology-based bounds tighteningcited by 10
  28. 2024Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifierscited by 10
  29. 2022Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systemscited by 9
  30. 2022QEBVerif: Quantization Error Bound Verification of Neural Networkscited by 9
  31. 2025Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verificationcited by 9
  32. 2021DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splittingcited by 8
  33. 2021Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networkscited by 8
  34. 2022Tighter Abstract Queries in Neural Network Verificationcited by 8
  35. 2023Machine Learning with Requirements: a Manifestocited by 8
  36. 2024Interval Abstractions for Robust Counterfactual Explanationscited by 7
  37. 2024ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networkscited by 7
  38. 2021Customizable Reference Runtime Monitoring of Neural Networks using Resolution Boxescited by 6

50 most cited of 126 All 126 (JSON)