mlsanityData to 14 Oct 2026

Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence

arXiv 2311.15782 ↗First posted 27 Nov 2023cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks. On the other hand, various model compression techniques, including pruning and quantization, can reduce the size of the network while preserving its accuracy. Several recent studies have addressed the relationship between model compression and adversarial robustness, while some experiments have reported contradictory results. This work summarizes available evidence and discusses possible explanations for the observed effects.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 56 of its 67 references that are in the map. First posted on arXiv 27 Nov 2023.

Builds on

56 of 67 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  10. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  12. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
38 more
  1. 2016Wide Residual Networkscited by 3,070
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  4. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,877
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2016Pruning Filters for Efficient ConvNetscited by 1,143
  12. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  13. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  14. 2019Adversarial Training for Free!cited by 643
  15. 2018Rethinking the Value of Network Pruningcited by 599
  16. 2020Overfitting in adversarially robust deep learningcited by 506
  17. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  18. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  19. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  20. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 316
  21. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 292
  22. 2019Adversarial Examples Improve Image Recognitioncited by 286
  23. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  24. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 217
  25. 2020Understanding and Improving Fast Adversarial Trainingcited by 214
  26. 2020Bag of Tricks for Adversarial Trainingcited by 200
  27. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 182
  28. 2017Data-Driven Sparse Structure Selection for Deep Neural Networkscited by 181
  29. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  30. 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
  31. 2019Defensive Quantization: When Efficiency Meets Robustnesscited by 95
  32. 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
  33. 2019And the Bit Goes Down: Revisiting the Quantization of Neural Networkscited by 78
  34. 2018Sparse DNNs with Improved Adversarial Robustnesscited by 72
  35. 2019Model Compression with Adversarial Robustness: A Unified Optimization Frameworkcited by 71
  36. 2019Neural Network Pruning with Residual-Connections and Limited-Datacited by 52
  37. 2020Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inferencecited by 45
  38. 2017Structured Bayesian Pruning via Log-Normal Multiplicative Noisecited by 39

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuningcited by 26
  2. 2024Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustnesscited by 10
  3. 2025Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerabilitycited by 7
  4. 2024Iterative Filter Pruning for Concatenation-based CNN Architecturescited by 4
  5. 2025On the Interaction of Compressibility and Adversarial Robustnesscited by 2
  6. 2026Understanding Fault Tolerance of Adversarially Robust Pruned Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Hardening DNNs against Transfer Attacks during Network Compression using Greedy Adversarial Pruning
  2. 2025Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
  3. 2024Robustness to distribution shifts of compressed networks for edge devices
  4. 2024Investigating the Impact of Quantization on Adversarial Robustness
  5. 2024Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models
  6. 2022Pruning Adversarially Robust Neural Networks without Adversarial Examples
  7. 2024Properties that allow or prohibit transferability of adversarial attacks among quantized networks
  8. 2024Effective Interplay between Sparsity and Quantization: From Theory to Practice