mlsanityData to 14 Oct 2026

NNV3: Expanding Neural Network Verification to New Architectures and Domains

arXiv 2609.30050 ↗First posted 24 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present NNV3, the latest version of the Neural Network Verification (NNV) tool, a MATLAB framework for formal verification of deep learning models and learning-enabled cyber-physical systems. Building on the set-based reachability foundation of NNV 1.0 (FFNNs, CNNs, NNCS) and NNV 2.0 (RNNs, SSNNs, neural ODEs), NNV3 introduces new members of the Star-set family: ModelStar for verifying networks under weight perturbation, VolumeStar for video and 3D volumetric inputs, and GraphStar for graph neural networks. A conformal-inference-based probabilistic reachability mode complements sound analysis for problems where deterministic verification is intractable, while FairNNV certifies counterfactual and individual fairness properties over continuous input regions. NNV3 introduces new benchmarks for malware detection, graph-based power-system models, medical imaging, variable-length time series data, and action recognition. NNV3 also incorporates tutorials and developer guides through a unified documentation site. This paper details these major updates, demonstrating NNV's maturation into a comprehensive, robust, and accessible verification tool for a diverse range of AI systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 45 of its 88 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

45 of 88 references.

References · 45

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  3. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  6. 2019Strategies for Pre-training Graph Neural Networkscited by 971
  7. 2017Counterfactual Fairnesscited by 804
  8. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  9. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
  10. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 187
  11. 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
  12. 2018Verisig: verifying safety properties of hybrid systems with neural network controllerscited by 84
33 more
  1. 2024Marabou 2.0: A Versatile Formal Analyzer of Neural Networkscited by 81
  2. 2018A Survey on Methods and Theories of Quantized Neural Networkscited by 75
  3. 2020Verification of Deep Convolutional Neural Networks Using ImageStarscited by 75
  4. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  5. 2023First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)cited by 58
  6. 2020Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbationcited by 57
  7. 2019Quantitative Verification of Neural Networks And its Security Applicationscited by 56
  8. 2019Perfectly Parallel Fairness Certification of Neural Networkscited by 42
  9. 2023The Fourth International Verification of Neural Networks Competition (VNN-COMP 2023): Summary and Resultscited by 38
  10. 2021Scalable Certified Segmentation via Randomized Smoothingcited by 35
  11. 2020Abstraction based Output Range Analysis for Neural Networkscited by 34
  12. 2019JuliaReach: a Toolbox for Set-Based Reachabilitycited by 28
  13. 2020Scalable Verification of Quantized Neural Networks (Technical Report)cited by 28
  14. 2024Provably Robust Conformal Prediction with Improved Efficiencycited by 27
  15. 2025The 6th International Verification of Neural Networks Competition (VNN-COMP 2025): Summary and Resultscited by 27
  16. 2020Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruptioncited by 26
  17. 2021Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopescited by 26
  18. 2020Justicia: A Stochastic SAT Approach to Formally Verify Fairnesscited by 25
  19. 2023A DPLL(T) Framework for Verifying Deep Neural Networkscited by 24
  20. 2022GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothingcited by 23
  21. 2021Formalizing Generalization and Robustness of Neural Networks to Weight Perturbationscited by 22
  22. 2022Scalable Verification of GNN-based Job Schedulerscited by 19
  23. 2024PowerGraph: A power grid benchmark dataset for graph neural networkscited by 19
  24. 2019Robustness Guarantees for Deep Neural Networks on Videoscited by 14
  25. 2020Adversarial Immunization for Certifiable Robustness on Graphscited by 14
  26. 2022Computing-In-Memory Neural Network Accelerators for Safety-Critical Systems: Can Small Device Variations Be Disastrous?cited by 12
  27. 2024Verifying message-passing neural networks via topology-based bounds tighteningcited by 10
  28. 2021Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networkscited by 8
  29. 2024Formal Verification of Graph Convolutional Networks with Uncertain Node Features and Uncertain Graph Structurecited by 8
  30. 2025Exact Verification of Graph Neural Networks with Incremental Constraint Solvingcited by 4
  31. 2025Probabilistic Robustness Analysis in High Dimensional Space: Application to Semantic Segmentation Networkcited by 3
  32. 2023Robustness Verification of Deep Neural Networks using Star-Based Reachability Analysis with Variable-Length Time Series Inputcited by 2
  33. 2026VNN-LIB 2.0: Rigorous Foundations for Neural Network Verificationcited by 1

Built on by

Not cited yet.