Boosting Fast Adversarial Training with Learnable Adversarial Initialization

by   Xiaojun Jia, et al.
The Chinese University of Hong Kong, Shenzhen

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating gradients at multiple steps in generating adversarial examples. To boost training efficiency, fast gradient sign method (FGSM) is adopted in fast AT methods by calculating gradient only once. Unfortunately, the robustness is far from satisfactory. One reason may arise from the initialization fashion. Existing fast AT generally uses a random sample-agnostic initialization, which facilitates the efficiency yet hinders a further robustness improvement. Up to now, the initialization in fast AT is still not extensively explored. In this paper, we boost fast AT with a sample-dependent adversarial initialization, i.e., an output from a generative network conditioned on a benign image and its gradient information from the target network. As the generative network and the target network are optimized jointly in the training phase, the former can adaptively generate an effective initialization with respect to the latter, which motivates gradually improved robustness. Experimental evaluations on four benchmark databases demonstrate the superiority of our proposed method over state-of-the-art fast AT methods, as well as comparable robustness to advanced multi-step AT methods. The code is released at


page 1

page 2

page 11

page 13


Prior-Guided Adversarial Initialization for Fast Adversarial Training

Fast adversarial training (FAT) effectively improves the efficiency of s...

Efficient Robust Training via Backward Smoothing

Adversarial training is so far the most effective strategy in defending ...

LAS-AT: Adversarial Training with Learnable Attack Strategy

Adversarial training (AT) is always formulated as a minimax problem, of ...

Towards Speeding up Adversarial Training in Latent Spaces

Adversarial training is wildly considered as the most effective way to d...

Fast is better than free: Revisiting adversarial training

Adversarial training, a method for learning robust deep networks, is typ...

Improving Fast Adversarial Training with Prior-Guided Knowledge

Fast adversarial training (FAT) is an efficient method to improve robust...

Fast AdvProp

Adversarial Propagation (AdvProp) is an effective way to improve recogni...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset