mlsanityData to 14 Oct 2026

Relational DNN Verification With Cross Executional Bound Refinement

arXiv 2405.10143 ↗First posted 16 May 2024cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

We focus on verifying relational properties defined over deep neural networks (DNNs) such as robustness against universal adversarial perturbations (UAP), certified worst-case hamming distance for binary string classifications, etc. Precise verification of these properties requires reasoning about multiple executions of the same DNN. However, most of the existing works in DNN verification only handle properties defined over single executions and as a result, are imprecise for relational properties. Though few recent works for relational DNN verification, capture linear dependencies between the inputs of multiple executions, they do not leverage dependencies between the outputs of hidden layers producing imprecise results. We develop a scalable relational verifier RACoon that utilizes cross-execution dependencies at all layers of the DNN gaining substantial precision over SOTA baselines on a wide range of datasets, networks, and relational properties.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

32 of 48 references.

References · 32

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2021Convex optimizationcited by 2,515
  4. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  5. 2016End to End Learning for Self-Driving Carscited by 1,009
  6. 2016Universal adversarial perturbationscited by 784
  7. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  8. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 445
  9. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 242
  10. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 205
  11. 2020Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifierscited by 187
  12. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
20 more
  1. 2019Branch and Bound for Piecewise Linear Neural Network Verificationcited by 138
  2. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 125
  3. 2018Strong mixed-integer programming formulations for trained neural networkscited by 115
  4. 2022General Cutting Planes for Bound-Propagation-Based Neural Network Verificationcited by 103
  5. 2022Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Boundcited by 92
  6. 2019Adversarial camera stickers: A physical camera-based attack on deep learning systemscited by 70
  7. 2023First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)cited by 58
  8. 2020ReluDiff: Differential Verification of Deep Neural Networkscited by 29
  9. 2020NeuroDiff: Scalable Differential Verification of Neural Networks using Fine-Grained Approximationcited by 22
  10. 2022Double Sampling Randomized Smoothingcited by 22
  11. 2020Fast Geometric Projections for Local Robustness Certificationcited by 21
  12. 2019Adversarial Music: Real World Audio Adversary Against Wake-word Detection Systemcited by 20
  13. 2022BagFlip: A Certified Defense against Data Poisoningcited by 19
  14. 2022CertiFair: A Framework for Certified Global Fairness of Neural Networkscited by 17
  15. 2022Toward Certified Robustness Against Real-World Distribution Shiftscited by 16
  16. 2019Verification of Non-Linear Specifications for Neural Networkscited by 14
  17. 2020Abstract Neural Networkscited by 11
  18. 2021DeepCert: Verification of Contextually Relevant Robustness for Neural Network Image Classifierscited by 11
  19. 2020An efficient nonconvex reformulation of stagewise convex optimization problemscited by 7
  20. 2019An Empirical Investigation of Randomized Defenses against Adversarial Attackscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 3.

5 papers.

  1. 2024Revisiting Differential Verification: Equivalence Verification with Confidencecited by 4
  2. 2025Support is All You Need for Certified VAE Trainingcited by 0
  3. 2026Hybrid Robustness Verification for Spatio-Temporal Neural Networkscited by 0
  4. 2026Branch and Bound for Relational Verification of Neural Networkscited by 0
  5. 2026Exploring Solver-Level Warmstarting for Neural Network Verificationcited by 0