Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework
Not on the map. Why?
Abstract (arXiv)
Deep neural network models are used today in various applications of artificial intelligence, the strengthening of which, in the face of adversarial attacks is of particular importance. An appropriate solution to adversarial attacks is adversarial training, which reaches a trade-off between robustness and generalization. This paper introduces a novel framework (Layer Sustainability Analysis (LSA)) for the analysis of layer vulnerability in an arbitrary neural network in the scenario of adversarial attacks. LSA can be a helpful toolkit to assess deep neural networks and to extend the adversarial training approaches towards improving the sustainability of model layers via layer monitoring and analysis. The LSA framework identifies a list of Most Vulnerable Layers (MVL list) of the given network. The relative error, as a comparison measure, is used to evaluate representation sustainability of each layer against adversarial inputs. The proposed approach for obtaining robust neural networks to fend off adversarial attacks is based on a layer-wise regularization (LR) over LSA proposal(s) for adversarial training (AT); i.e. the AT-LR procedure. AT-LR could be used with any benchmark adversarial attack to reduce the vulnerability of network layers and to improve conventional adversarial training approaches. The proposed idea performs well theoretically and experimentally for state-of-the-art multilayer perceptron and convolutional neural network architectures. Compared with the AT-LR and its corresponding base adversarial training, the classification accuracy of more significant perturbations increased by 16.35%, 21.79%, and 10.730% on Moon, MNIST, and CIFAR-10 benchmark datasets, respectively. The LSA framework is available and published at https://github.com/khalooei/LSA.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 50 of its 72 references that are in the map. First posted on arXiv 5 Feb 2022.
Builds on
50 of 72 references.
References · 50
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Wide Residual Networkscited by 3,057
- 2016Adversarial examples in the physical worldcited by 1,762
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
- 2018Robustness May Be at Odds with Accuracycited by 873
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
38 more
- 2020Fast is better than free: Revisiting adversarial trainingcited by 723
- 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2020Overfitting in adversarially robust deep learningcited by 504
- 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
- 2020Time Series Forecasting With Deep Learning: A Surveycited by 457
- 2019On Evaluating Adversarial Robustnesscited by 442
- 2017Mitigating Adversarial Effects Through Randomizationcited by 382
- 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
- 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
- 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
- 2018Certified Defenses against Adversarial Examplescited by 305
- 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
- 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
- 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
- 2020Understanding and Improving Fast Adversarial Trainingcited by 213
- 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
- 2018Spatially Transformed Adversarial Examplescited by 195
- 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
- 2018Disentangling Adversarial Robustness and Generalizationcited by 171
- 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
- 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
- 2018Scaling provable adversarial defensescited by 141
- 2018Adversarial Attacks and Defences Competitioncited by 96
- 2018Adversarial examples from computational constraintscited by 79
- 2018Adversarial vulnerability for any classifiercited by 78
- 2015Adversarial Manipulation of Deep Representationscited by 56
- 2019Adversarial Defense by Restricting the Hidden Space of Deep Neural Networkscited by 56
- 2019Jacobian Adversarially Regularized Networks for Robustnesscited by 40
- 2019Survey on Deep Neural Networks in Speech and Vision Systemscited by 37
- 2017Regularizing deep networks using efficient layerwise adversarial trainingcited by 24
- 2018Combatting Adversarial Attacks through Denoising and Dimensionality Reduction: A Cascaded Autoencoder Approachcited by 10
- 2020FADER: Fast Adversarial Example Rejectioncited by 9
- 2019Cross-Layer Strategic Ensemble Defense Against Adversarial Examplescited by 7
- 2021Explaining Adversarial Vulnerability with a Data Sparsity Hypothesiscited by 4
- 2020Improving Resistance to Adversarial Deformations by Regularizing Gradientscited by 3
Built on by
Citing papers per year: 2023: 1; 2024: 1.
2 papers.