mlsanityData to 7 Oct 2026

DeepAbstract: Neural Network Abstraction for Accelerating Verification

arXiv 2006.13735 ↗First posted 24 Jun 2020cs.LO cs.AI cs.LGcited by 31

Not on the map. Why?

Abstract (arXiv)

While abstraction is a classic tool of verification to scale it up, it is not used very often for verifying neural networks. However, it can help with the still open task of scaling existing algorithms to state-of-the-art network architectures. We introduce an abstraction framework applicable to fully-connected feed-forward neural networks based on clustering of neurons that behave similarly on some inputs. For the particular case of ReLU, we additionally provide error bounds incurred by the abstraction. We show how the abstraction reduces the size of the network, while preserving its accuracy, and how verification results on the abstract network can be transferred back to the original network.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 9; 2023: 9; 2024: 2; 2025: 4; 2026: 1.

31 papers.

Sort:

By area:

  1. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  2. 2021Pruning and Slicing Neural Networks using Formal Verificationcited by 20
  3. 2022Verification-Aided Deep Ensemble Selectioncited by 18
  4. 2021BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networkscited by 17
  5. 2021Minimal Multi-Layer Modifications of Deep Neural Networkscited by 14
  6. 2021Towards Practical Robustness Analysis for DNNs based on PAC-Model Learningcited by 12
  7. 2022QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networkscited by 12
  8. 2023Distributionally Robust Statistical Verification with Imprecise Neural Networkscited by 12
  9. 2022Abstraction and Refinement: Towards Scalable and Exact Verification of Neural Networkscited by 11
  10. 2023Verifying Generalization in Deep Learningcited by 11
  11. 2021Shared Certificates for Neural Network Verificationcited by 10
  12. 2022On Neural Network Equivalence Checking using SMT Solverscited by 10
19 more
  1. 2022QEBVerif: Quantization Error Bound Verification of Neural Networkscited by 9
  2. 2022Tighter Abstract Queries in Neural Network Verificationcited by 8
  3. 2021Bisimulations for Neural Network Reductioncited by 6
  4. 2022On Optimizing Back-Substitution Methods for Neural Network Verificationcited by 6
  5. 2023Fully Automatic Neural Network Reduction for Formal Verificationcited by 6
  6. 2024DeepCDCL: An CDCL-based Neural Network Verification Frameworkcited by 6
  7. 2025Abstraction-Based Proof Production in Formal Verification of Neural Networkscited by 5
  8. 2023DelBugV: Delta-Debugging Neural Network Verifierscited by 3
  9. 2022Bridging the Gap between Artificial Intelligence and Artificial General Intelligence: A Ten Commandment Framework for Human-Like Intelligencecited by 2
  10. 2023Incremental Satisfiability Modulo Theory for Verification of Deep Neural Networkscited by 2
  11. 2025Verification of Bit-Flip Attacks against Quantized Neural Networkscited by 2
  12. 2025Mini-Batch Robustness Verification of Deep Neural Networkscited by 1
  13. 2025Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exitscited by 1
  14. 2023Scaling Model Checking for DNN Analysis via State-Space Reduction and Input Segmentation (Extended Version)cited by 0
  15. 2023Syntactic vs Semantic Linear Abstraction and Refinement of Neural Networkscited by 0
  16. 2023Verification of Neural Networks Local Differential Classification Privacycited by 0
  17. 2023AGNES: Abstraction-guided Framework for Deep Neural Networks Securitycited by 0
  18. 2024Patch Synthesis for Property Repair of Deep Neural Networkscited by 0
  19. 2026Talking with Verifiers: Automatic Specification Generation for Neural Network Verificationcited by 0