5 papers · 1 filter
Efficient Preference Poisoning Attack on Offline RLHF
Chenye Yang, Weiyu Xu, Lifeng Lai
Offline Reinforcement Learning from Human Feedback (RLHF) pipelines such as Direct Preference Optimization (DPO) train on a pre-collected preference dataset, which makes them vulne…
Learn to Change the World: Multi-level Reinforcement Learning with Model-Changing Actions
Ziqing Lu, Babak Hassibi, Lifeng Lai +1
Reinforcement learning usually assumes a given or sometimes even fixed environment in which an agent seeks an optimal policy to maximize its long-term discounted reward. In contras…
Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach
Ziqing Lu, Lifeng Lai, Weiyu Xu
Reinforcement learning (RL) for the Markov Decision Process (MDP) has emerged in many security-related applications, such as autonomous driving, financial decisions, and drone/robo…
Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems
Ziqing Lu, Guanlin Liu, Lifeng Lai +1
Finding optimal adversarial attack strategies is an important topic in reinforcement learning and the Markov decision process. Previous studies usually assume one all-knowing coord…
Distributed Dual Coordinate Ascent with Imbalanced Data on a General Tree Network
Myung Cho, Lifeng Lai, Weiyu Xu
In this paper, we investigate the impact of imbalanced data on the convergence of distributed dual coordinate ascent in a tree network for solving an empirical loss minimization pr…