paper-with-me

Papers

Reward-Preserving Attacks For Robust Reinforcement Learning

2026-01-12 · Lucas Schott, Elies Gherbi, Hatem Hajri, Sylvain Lamprier arxiv

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. We propose reward-preserving attacks, which adapt adversarial strength so that an $α$ fraction of the nominal-to-worst-case return gap remains achievable at each state. In deep RL, perturbation magnitudes $η$ are selected dynamically, using a learned critic $Q((s,a),η)$ that estimates the expected return of $α$-reward-preserving rollouts. For intermediate values of $α$, this adaptive training yields policies that are robust across a wide range of perturbation magnitudes while preserving nominal performance, outperforming fixed-radius and uniformly sampled-radius adversarial training.

📄 PDF Abstract BibTeX arXiv:2601.07118

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Reward Delay Attacks on Deep Reinforcement Learning

2022-09-08 · Anindya Sarkar, Jiarui Feng, Yevgeniy Vorobeychik, Christopher Gill 외

Most reinforcement learning algorithms implicitly assume strong synchrony. We present novel attacks targeting Q-learning that exploit a vulnerability entailed by this assumption by delaying the reward signal for a limite…

Deep Reinforcement LearningQ-Learningreinforcement-learningReinforcement Learning+1

Adaptive Reward-Poisoning Attacks against Reinforcement Learning

2020-03-27 · ICML 2020 1 · Xuezhou Zhang, Yuzhe ma, Adish Singla, Xiaojin Zhu

In reward-poisoning attacks against reinforcement learning (RL), an attacker can perturb the environment reward $r_t$ into $r_t+\delta_t$ at each step, with the goal of forcing the RL agent to learn a nefarious policy. W…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning

2022-05-30 · Yinglun Xu, Qi Zeng, Gagandeep Singh

We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment. We demonstrate the intrinsic…

Data PoisoningDeep Reinforcement LearningMuJoCoreinforcement-learning+2

Reinforcement Learning-Based Black-Box Model Inversion Attacks

2023-04-10 · CVPR 2023 1 · Gyojin Han, Jaehyun Choi, Haeil Lee, Junmo Kim

Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model. Recently, white-box model inversion attacks leveraging Generative…

modelPrivacy Preservingreinforcement-learningReinforcement Learning

Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning

2022-08-29 · Anshuka Rangi, Haifeng Xu, Long Tran-Thanh, Massimo Franceschetti

To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{any} order-optimal learning algorithm towards a targeted policy in episodic RL and ex…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)