Learning to Defense by Learning to Attack

11/03/2018
by   Zhehui Chen, et al.
0

Adversarial training provides a principled approach for training robust neural networks. From an optimization perspective, the adversarial training is essentially solving a minmax robust optimization problem. The outer minimization is trying to learn a robust classifier, while the inner maximization is trying to generate adversarial samples. Unfortunately, such a minmax problem is very difficult to solve due to the lack of convex-concave structure. This work proposes a new adversarial training method based on a general learning-to-learn framework. Specifically, instead of applying the existing hand-design algorithms for the inner problem, we learn an optimizer, which is parametrized as a convolutional neural network. At the same time, a robust classifier is learned to defense the adversarial attack generated by the learned optimizer. Our experiments demonstrate that our proposed method significantly outperforms existing adversarial training methods on CIFAR-10 and CIFAR-100 datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/25/2020

Improved Adversarial Training via Learned Optimizer

Adversarial attack has recently become a tremendous threat to deep learn...
research
10/30/2021

Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach

Current SOTA adversarially robust models are mostly based on adversarial...
research
05/02/2022

Enhancing Adversarial Training with Feature Separability

Deep Neural Network (DNN) are vulnerable to adversarial attacks. As a co...
research
02/09/2021

Provable Defense Against Delusive Poisoning

Delusive poisoning is a special kind of attack to obstruct learning, whe...
research
07/21/2023

Improving Viewpoint Robustness for Visual Recognition via Adversarial Training

Viewpoint invariance remains challenging for visual recognition in the 3...
research
05/28/2021

Robust Regularization with Adversarial Labelling of Perturbed Samples

Recent researches have suggested that the predictive accuracy of neural ...
research
06/19/2019

Convergence of Adversarial Training in Overparametrized Networks

Neural networks are vulnerable to adversarial examples, i.e. inputs that...

Please sign up or login with your details

Forgot password? Click here to reset