mlsanityData to 7 Oct 2026

Reachability Analysis of Convolutional Neural Networks

arXiv 2106.12074 ↗First posted 22 Jun 2021cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep convolutional neural networks have been widely employed as an effective technique to handle complex and practical problems. However, one of the fundamental problems is the lack of formal methods to analyze their behavior. To address this challenge, we propose an approach to compute the exact reachable sets of a network given an input domain, where the reachable set is represented by the face lattice structure. Besides the computation of reachable sets, our approach is also capable of backtracking to the input domain given an output reachable set. Therefore, a full analysis of a network's behavior can be realized. In addition, an approach for fast analysis is also introduced, which conducts fast computation of reachable sets by considering selected sensitive neurons in each layer. The exact pixel-level reachability analysis method is evaluated on a CNN for the CIFAR10 dataset and compared to related works. The fast analysis method is evaluated over a CNN CIFAR10 dataset and VGG16 architecture for the ImageNet dataset.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 22 Jun 2021.

Builds on

39 of 55 references.

References · 39

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  7. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  8. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  9. 2017One pixel attack for fooling deep neural networkscited by 579
  10. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  11. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  12. 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 416
27 more
  1. 2014On the Number of Linear Regions of Deep Neural Networkscited by 378
  2. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  3. 2018Certified Defenses against Adversarial Examplescited by 305
  4. 2016Safety Verification of Deep Neural Networkscited by 262
  5. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  6. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 249
  7. 2017Formal Verification of Piece-Wise Linear Feed-Forward Neural Networkscited by 241
  8. 2018Formal Security Analysis of Neural Networks using Symbolic Intervalscited by 185
  9. 2017Visualizing Deep Neural Network Decisions: Prediction Difference Analysiscited by 166
  10. 2019Complexity of Linear Regions in Deep Networkscited by 166
  11. 2017Bounding and Counting Linear Regions of Deep Neural Networkscited by 161
  12. 2020NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systemscited by 128
  13. 2017An approach to reachability analysis for feed-forward ReLU neural networkscited by 126
  14. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  15. 2018SparseFool: a few pixels make a big differencecited by 94
  16. 2016Measuring Neural Net Robustness with Constraintscited by 90
  17. 2018Automatic Instrument Segmentation in Robot-Assisted Surgery Using Deep Learningcited by 81
  18. 2017Output Reachable Set Estimation and Verification for Multi-Layer Neural Networkscited by 79
  19. 2020Verification of Deep Convolutional Neural Networks Using ImageStarscited by 75
  20. 2020The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verificationcited by 50
  21. 2019Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustnesscited by 40
  22. 2020One-pixel Signature: Characterizing CNN Models for Backdoor Detectioncited by 34
  23. 2017Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activationscited by 22
  24. 2018Formal Verification of CNN-based Perception Systemscited by 13
  25. 2020Reachability Analysis for Feed-Forward Neural Networks using Face Latticescited by 11
  26. 2017Deep EndoVO: A Recurrent Convolutional Neural Network (RCNN) based Visual Odometry Approach for Endoscopic Capsule Robotscited by 10
  27. 2018Attacking Convolutional Neural Network using Differential Evolutioncited by 2

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 0; 2025: 1.

4 papers.

  1. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  2. 2022An Abstraction-Refinement Approach to Verifying Convolutional Neural Networkscited by 24
  3. 2021Neural Network Repair with Reachability Analysiscited by 19
  4. 2025Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopescited by 0