Benchmarking Adversarial Robustness of Compressed Deep Learning Models
Not on the map. Why?
Abstract (arXiv)
The increasing size of Deep Neural Networks (DNNs) poses a pressing need for model compression, particularly when employed on resource constrained devices. Concurrently, the susceptibility of DNNs to adversarial attacks presents another significant hurdle. Despite substantial research on both model compression and adversarial robustness, their joint examination remains underexplored. Our study bridges this gap, seeking to understand the effect of adversarial inputs crafted for base models on their pruned versions. To examine this relationship, we have developed a comprehensive benchmark across diverse adversarial attacks and popular DNN models. We uniquely focus on models not previously exposed to adversarial training and apply pruning schemes optimized for accuracy and performance. Our findings reveal that while the benefits of pruning enhanced generalizability, compression, and faster inference times are preserved, adversarial robustness remains comparable to the base model. This suggests that model compression while offering its unique advantages, does not undermine adversarial robustness.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 47 of its 59 references that are in the map. First posted on arXiv 16 Aug 2023.
Builds on
47 of 59 references.
References · 47
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
- 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
- 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
- 2016Adversarial examples in the physical worldcited by 1,769
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
35 more
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2016Universal adversarial perturbationscited by 784
- 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
- 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 637
- 2018Rethinking the Value of Network Pruningcited by 599
- 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
- 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
- 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
- 2017Variational Dropout Sparsifies Deep Neural Networkscited by 265
- 2018Adversarial Attacks and Defences: A Surveycited by 259
- 2018Generating Adversarial Examples with Adversarial Networkscited by 258
- 2019Simple Black-box Adversarial Attackscited by 251
- 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
- 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
- 2017The Space of Transferable Adversarial Examplescited by 158
- 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 155
- 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 147
- 2019Adversarial Robustness vs Model Compression, or Both?cited by 98
- 2019Wasserstein Adversarial Examples via Projected Sinkhorn Iterationscited by 89
- 2020Gradient Flow in Sparse Neural Networks and How Lottery Tickets Wincited by 77
- 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
- 2021Boosting Adversarial Transferability through Enhanced Momentumcited by 54
- 2022Pruning's Effect on Generalization Through the Lens of Training and Regularizationcited by 31
- 2022DropNet: Reducing Neural Network Complexity via Iterative Pruningcited by 29
- 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
- 2021On the Effect of Pruning on Adversarial Robustnesscited by 23
- 2021Pruning Randomly Initialized Neural Networks with Iterative Randomizationcited by 20
- 2020Neural Network Compression Framework for fast model inferencecited by 18
- 2020Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificatescited by 18
- 2019Benchmarking Adversarial Robustnesscited by 15
- 2022Can pruning improve certified robustness of neural networks?cited by 14
- 2020GAP++: Learning to generate target-conditioned adversarial examplescited by 5
Built on by
Citing papers per year: 2023: 1; 2024: 2.
3 papers.