Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

2017-01-16 · Vahid Behzadan, Arslan Munir

Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs) are also vulnerable to adversarial input perturbations, and verify the transferability of adversarial examples across different DQN models. Furthermore, we present a novel class of attacks based on this vulnerability that enable policy manipulation and induction in the learning process of DQNs. We propose an attack mechanism that exploits the transferability of adversarial examples to implement policy induction attacks on DQNs, and demonstrate its efficacy and impact through experimental study of a game-learning scenario.

📄 PDF Abstract BibTeX arXiv:1701.04143

Code (1)

coderatwork7/attack tf

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

DQN A DQN, or Deep Q-Network, approximates a state-value function in a Q-Learning framework with a neural network. In the Atari…

Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noise

2018-06-04 · Vahid Behzadan, Arslan Munir

Recent developments have established the vulnerability of deep reinforcement learning to policy manipulation attacks via intentionally perturbed inputs, known as adversarial examples. In this work, we propose a technique…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Inception: Efficiently Computable Misinformation Attacks on Markov Games

2024-06-24 · Jeremy McMahan, Young Wu, Yudong Chen, Xiaojin Zhu 외

We study security threats to Markov games due to information asymmetry and misinformation. We consider an attacker player who can spread misinformation about its reward function to influence the robust victim player's be…

Misinformation

Whatever Does Not Kill Deep Reinforcement Learning, Makes It Stronger

2017-12-23 · Vahid Behzadan, Arslan Munir

Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Is poisoning a real threat to LLM alignment? Maybe more so than you think

2024-06-17 · Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang 외

Recent advancements in Reinforcement Learning with Human Feedback (RLHF) have significantly impacted the alignment of Large Language Models (LLMs). The sensitivity of reinforcement learning algorithms such as Proximal Po…

reinforcement-learning Reinforcement Learning

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses

2024-05-18 · Thanh Nguyen, Tung M. Luu, Tri Ton, Chang D. Yoo

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning i…

D4RL Offline RL Reinforcement Learning (RL)