Recent Advances in Adversarial Training for Adversarial Robustness

Abstract

Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models intrinsically. During the last few years, adversarial training has been studied and discussed from various aspects. A variety of improvements and developments of adversarial training are proposed, which were, however, neglected in existing surveys. For the first time in this survey, we systematically review the recent progress on adversarial training for adversarial robustness with a novel taxonomy. Then we discuss the generalization problems in adversarial training from three perspectives. Finally, we highlight the challenges which are not fully tackled and present potential future directions.

arXiv commentaccepted by International Joint Conference on Artificial Intelligence (IJCAI-21)

References in corpus (38)

• mixup: Beyond Empirical Risk Minimization
• Improved Regularization of Convolutional Neural Networks with Cutout
• Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
• The Space of Transferable Adversarial Examples
• Using Pre-Training Can Improve Model Robustness and Uncertainty
• Adversarial Examples Are Not Bugs, They Are Features
• Adversarial Machine Learning at Scale
• Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization
• Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• Learning with a Strong Adversary
• Towards the first adversarially robust neural network model on MNIST
• Adversarial Robustness through Local Linearization
• Improving Adversarial Robustness via Promoting Ensemble Diversity
• On the Convergence and Robustness of Adversarial Training
• Adversarial Attack on Graph Structured Data
• Adversarial Training Can Hurt Generalization
• Adversarial Training and Robustness for Multiple Perturbations
• Improving Adversarial Robustness of Ensembles with Diversity Training
• Smooth Adversarial Training
• Adversarial Examples for Semantic Segmentation and Object Detection
• MMA Training: Direct Input Space Margin Maximization through Adversarial Training
• Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
• Evaluating and Understanding the Robustness of Adversarial Logit Pairing
• Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets
• Metric Learning for Adversarial Robustness
• Adversarial Examples in Modern Machine Learning: A Review
• Understanding and Improving Fast Adversarial Training
• Robustness to Adversarial Perturbations in Learning from Incomplete Data
• Adversarial Distributional Training for Robust Deep Learning
• Curriculum Adversarial Training
• Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey
• Transfer of Adversarial Robustness Between Perturbation Types
• Towards Understanding Fast Adversarial Training
• PAC-learning in the presence of evasion adversaries
• Bag of Tricks for Adversarial Training
• On the Generalization Properties of Adversarial Training
• Understanding Catastrophic Overfitting in Single-step Adversarial Training
• Regularizers for Single-step Adversarial Training

Cited by in corpus (5)

• Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention
• Adversarial Purification through Representation Disentanglement
• Adaptive Adversarial Training Does Not Increase Recourse Costs
• Domain Invariant Adversarial Learning
• Towards Optimal Randomized Strategies in Adversarial Example Game