LAS-AT: Adversarial Training with Learnable Attack Strategy
Authors:
- 1 June 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13388-13398
Abstract
Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adver-sarial examples (AEs). Most previous methods adopt Projected Gradient Decent (PGD) with manually specifying attack parameters for AE generation. A combination of the attack parameters can be referred to as an attack strategy. Several works have revealed that using a fixed attack strategy to generate AEs during the whole training phase limits the model robustness and propose to exploit different attack strategies at different training stages to improve robustness. But those multi-stage handcrafted attack strategies need much domain expertise, and the robustness improvement is limited. In this paper, we propose a novel framework for adversarial training by introducing the concept of “learnable attack strategy”, dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness. Our framework is composed of a target network that uses AEs for training to improve robustness, and a strategy network that produces attack strategies to control the AE generation. Experimental evaluations on three benchmark databases demonstrate the superiority of the proposed method. The code is released at https://github.com/jiaxiaojunQAQ/LAS-AT.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62025604,62076213,62006217)
This publication has 21 references indexed in Scilit:
- Adversarial Defense Via Local Flatness Regularization2020
- Adversarial Vertex Mixup: Toward Better Adversarially Robust Generalization2020
- Image elementary manifold and its application in image analysis2018
- Boosting Adversarial Attacks with Momentum2018
- Jointly Optimize Data Augmentation and Network Training: Adversarial Data Augmentation in Human Pose Estimation2018
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009
- Simple statistical gradient-following algorithms for connectionist reinforcement learningMachine Learning, 1992