Adaptive perturbation adversarial training: based on reinforcement learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the …
Deep Reinforcement LearningMuJoCoReward-Preserving Attacks For Robust Reinforcement Learning
Adversarial training in reinforcement learning (RL) is challenging because perturbations cascade through trajectories and compound over time, making fixed-strength attacks either overly destructive or too conservative. W…
Reinforcement LearningRobust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks
Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adve…
Adversarial AttackAdversarial DefenseDeep Reinforcement LearningAdversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control
Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults…
Reinforcement LearningAsymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation
Adversarial training has been proposed to protect machine learning models against adversarial attacks. This paper focuses on adversarial training under $\ell_\infty$-perturbation, which has recently attracted much resear…
Variable Selection