Optimal Cost Constrained Adversarial Attacks For Multiple Agent Systems

no code implementations • 1 Nov 2023 • Ziqing Lu, Guanlin Liu, Lifeng Cai, Weiyu Xu

Finding optimal adversarial attack strategies is an important topic in reinforcement learning and the Markov decision process.

Adversarial Attack

Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty

no code implementations • 15 Jul 2023 • Guanlin Liu, Zhihan Zhou, Han Liu, Lifeng Lai

Robust reinforcement learning (RL) aims to find a policy that optimizes the worst-case performance in the face of uncertainties.

reinforcement-learning Reinforcement Learning (RL)

Efficient Action Poisoning Attacks on Linear Contextual Bandits

no code implementations • 10 Dec 2021 • Guanlin Liu, Lifeng Lai

We show that, in both white-box and black-box settings, the proposed attack schemes can force the LinUCB agent to pull a target arm very frequently by spending only logarithm cost.

Multi-Armed Bandits

Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning

no code implementations • NeurIPS 2021 • Guanlin Liu, Lifeng Lai

In this paper, we introduce a new class of attacks named action poisoning attacks, where an adversary can change the action signal selected by the agent.

reinforcement-learning Reinforcement Learning (RL)

Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defense

no code implementations • 19 Feb 2020 • Guanlin Liu, Lifeng Lai

To defend against this class of attacks, we introduce a novel algorithm that is robust to action-manipulation attacks when an upper bound for the total attack cost is given.