DeepAI AI Chat
Log In Sign Up

Adaptive perturbation adversarial training: based on reinforcement learning

by   Zhishen Nie, et al.
Yunnan University

Adversarial training has become the primary method to defend against adversarial samples. However, it is hard to practically apply due to many shortcomings. One of the shortcomings of adversarial training is that it will reduce the recognition accuracy of normal samples. Adaptive perturbation adversarial training is proposed to alleviate this problem. It uses marginal adversarial samples that are close to the decision boundary but does not cross the decision boundary for adversarial training, which improves the accuracy of model recognition while maintaining the robustness of the model. However, searching for marginal adversarial samples brings additional computational costs. This paper proposes a method for finding marginal adversarial samples based on reinforcement learning, and combines it with the latest fast adversarial training technology, which effectively speeds up training process and reduces training costs.


page 1

page 2

page 3

page 4


Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets

Adversarial training is by far the most successful strategy for improvin...

Exploring Model Robustness with Adaptive Networks and Improved Adversarial Training

Adversarial training has proven to be effective in hardening networks ag...

Adaptive Adversarial Training for Meta Reinforcement Learning

Meta Reinforcement Learning (MRL) enables an agent to learn from a limit...

Towards Speeding up Adversarial Training in Latent Spaces

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

Understanding Catastrophic Overfitting in Adversarial Training

Recently, FGSM adversarial training is found to be able to train a robus...

Towards Interpretability of Speech Pause in Dementia Detection using Adversarial Learning

Speech pause is an effective biomarker in dementia detection. Recent dee...

Moment-based Adversarial Training for Embodied Language Comprehension

In this paper, we focus on a vision-and-language task in which a robot i...