mlsanityData to 7 Oct 2026

Parallelization Techniques for Verifying Neural Networks

arXiv 2004.08440 ↗First posted 17 Apr 2020cs.LO cs.AI cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parallel computing to improve the scalability of neural network verification. We introduce an algorithm based on partitioning the verification problem in an iterative manner and explore two partitioning strategies, that work by partitioning the input space or by case splitting on the phases of the neuron activations, respectively. We also introduce a highly parallelizable pre-processing algorithm that uses the neuron activation phases to simplify the neural network verification problems. An extensive experimental evaluation shows the benefit of these techniques on both existing benchmarks and new benchmarks from the aviation domain. A preliminary experiment with ultra-scaling our algorithm using a large distributed cloud-based platform also shows promising results.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 13; 2023: 7; 2024: 2; 2025: 1; 2026: 4.

36 papers.

Sort:

  1. 2024Marabou 2.0: A Versatile Formal Analyzer of Neural Networkscited by 81
  2. 2021The Second International Verification of Neural Networks Competition (VNN-COMP 2021): Summary and Resultscited by 71
  3. 2022Towards Formal XAI: Formally Approximate Minimal Explanations of Neural Networkscited by 42
  4. 2022The Third International Verification of Neural Networks Competition (VNN-COMP 2022): Summary and Resultscited by 39
  5. 2021OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systemscited by 37
  6. 2021Towards Scalable Verification of Deep Reinforcement Learningcited by 33
  7. 2022Verifying Learning-Based Robotic Navigation Systemscited by 33
  8. 2022VeriX: Towards Verified Explainability of Deep Neural Networkscited by 30
  9. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  10. 2022Efficient Neural Network Analysis with Sum-of-Infeasibilitiescited by 24
  11. 2023Formally Explaining Neural Networks within Reactive Systemscited by 24
  12. 2023A DPLL(T) Framework for Verifying Deep Neural Networkscited by 23
24 more
  1. 2022Neural Network Verification with Proof Productioncited by 22
  2. 2021Pruning and Slicing Neural Networks using Formal Verificationcited by 20
  3. 2022Verification-Aided Deep Ensemble Selectioncited by 18
  4. 2022Scalable Verification of GNN-based Job Schedulerscited by 18
  5. 2021Minimal Multi-Layer Modifications of Deep Neural Networkscited by 14
  6. 2021DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifierscited by 11
  7. 2022Constrained Reinforcement Learning for Robotics via Scenario-Based Programmingcited by 11
  8. 2023Verifying Generalization in Deep Learningcited by 11
  9. 2021RoMA: a Method for Neural Network Robustness Measurement and Assessmentcited by 10
  10. 2022Tighter Abstract Queries in Neural Network Verificationcited by 8
  11. 2021Self-Correcting Neural Networks For Safe Classificationcited by 4
  12. 2022Boosting Robustness Verification of Semantic Feature Neighborhoodscited by 4
  13. 2023DelBugV: Delta-Debugging Neural Network Verifierscited by 3
  14. 2025PICID: Proof-Driven Clause Learning in Neural Network Verificationcited by 3
  15. 2021ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputscited by 2
  16. 2022Negative Selection Approach to support Formal Verification and Validation of BlackBox Models' Input Constraintscited by 2
  17. 2023UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networkscited by 2
  18. 2024Boosting Few-Pixel Robustness Verification via Covering Verification Designscited by 2
  19. 2026Incremental Neural Network Verification via Learned Conflictscited by 2
  20. 2026Lookahead Branching for Neural Network Verificationcited by 1
  21. 2023Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)cited by 0
  22. 2023Verification of Neural Networks Local Differential Classification Privacycited by 0
  23. 2026veriFIRE: an Industrial Case Study in Verifying Consistency Properties for a DNN-Based Wildfire Detection Systemcited by 0
  24. 2026Verifying Neural Networks with Reinforcement Learningcited by 0