Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization

• URL: http://arxiv.org/abs/2410.03376v1
• Date: Fri, 4 Oct 2024 12:41:54 GMT
• Title: Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization
• Authors: Tung M. Luu, Thanh Nguyen, Tee Joshua Tian Jin, Sungwoon Kim, Chang D. Yoo,
• Abstract summary: Well-performing reinforcement learning (RL) agents often lack resilience against adversarial perturbations during deployment. This highlights the importance of building a robust agent before deploying it in the real world. In this work, we study an input transformation-based defense for RL.
• Score: 18.56608399174564
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent studies reveal that well-performing reinforcement learning (RL) agents in training often lack resilience against adversarial perturbations during deployment. This highlights the importance of building a robust agent before deploying it in the real world. Most prior works focus on developing robust training-based procedures to tackle this problem, including enhancing the robustness of the deep neural network component itself or adversarially training the agent on strong attacks. In this work, we instead study an input transformation-based defense for RL. Specifically, we propose using a variant of vector quantization (VQ) as a transformation for input observations, which is then used to reduce the space of adversarial attacks during testing, resulting in the transformed observations being less affected by attacks. Our method is computationally efficient and seamlessly integrates with adversarial training, further enhancing the robustness of RL agents against adversarial attacks. Through extensive experiments in multiple environments, we demonstrate that using VQ as the input transformation effectively defends against adversarial attacks on the agent's observations.

Related papers

• On the Perturbed States for Transformed Input-robust Reinforcement Learning [24.11603621594292]
  Reinforcement Learning (RL) agents exhibit vulnerability to adversarial perturbations in input observations during deployment. We introduce two principles for applying transformation-based defenses in learning robust RL agents. Experiments on multiple MuJoCo environments demonstrate that input transformation-based defenses defend against several adversaries.
  arXiv  Detail & Related papers  (2024-07-31T05:31:28Z)
• GenFighter: A Generative and Evolutive Textual Attack Removal [6.044610337297754]
  Adrial attacks pose significant challenges to deep neural networks (DNNs) such as Transformer models in natural language processing (NLP) This paper introduces a novel defense strategy, called GenFighter, which enhances adversarial robustness by learning and reasoning on the training classification distribution. We show that GenFighter outperforms state-of-the-art defenses in accuracy under attack and attack success rate metrics.
  arXiv  Detail & Related papers  (2024-04-17T16:32:13Z)
• Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey [8.463282079069362]
  Deep Reinforcement Learning (DRL) is an approach for training autonomous agents across various complex environments. It remains susceptible to minor conditions variations, raising concerns about its reliability in real-world applications. A way to improve robustness of DRL to unknown changes in the conditions is through Adversarial Training.
  arXiv  Detail & Related papers  (2024-03-01T10:16:46Z)
• On the Difficulty of Defending Contrastive Learning against Backdoor Attacks [58.824074124014224]
  We show how contrastive backdoor attacks operate through distinctive mechanisms. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks.
  arXiv  Detail & Related papers  (2023-12-14T15:54:52Z)
• Enhancing Adversarial Training with Feature Separability [52.39305978984573]
  We introduce a new concept of adversarial training graph (ATG) with which the proposed adversarial training with feature separability (ATFS) enables to boost the intra-class feature similarity and increase inter-class feature variance. Through comprehensive experiments, we demonstrate that the proposed ATFS framework significantly improves both clean and robust performance.
  arXiv  Detail & Related papers  (2022-05-02T04:04:23Z)
• Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness [53.094682754683255]
  We propose a Model-Agnostic Meta-Attack (MAMA) approach to discover stronger attack algorithms automatically. Our method learns the in adversarial attacks parameterized by a recurrent neural network. We develop a model-agnostic training algorithm to improve the ability of the learned when attacking unseen defenses.
  arXiv  Detail & Related papers  (2021-10-13T13:54:24Z)
• Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning [32.12283927682007]
  Deep reinforcement learning models are vulnerable to adversarial attacks which can decrease the victim's total reward by manipulating the observations. We reformulate the problem of adversarial attacks in function space and separate the previous gradient based attacks into several subspaces. In the first stage, we train a deceptive policy by hacking the environment, and discover a set of trajectories routing to the lowest reward. Our method provides a tighter theoretical upper bound for the attacked agent's performance than the existing approaches.
  arXiv  Detail & Related papers  (2021-06-30T07:41:51Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• Robust Reinforcement Learning on State Observations with Learned Optimal Adversary [86.0846119254031]
  We study the robustness of reinforcement learning with adversarially perturbed state observations. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than previous ones.
  arXiv  Detail & Related papers  (2021-01-21T05:38:52Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.