Inception: Efficiently Computable Misinformation Attacks on Markov Games
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 behavior. Given a fixed fake reward function, we derive the victim's policy under worst-case rationality and present polynomial-time algorithms to compute the attacker's optimal worst-case policy based on linear programming and backward induction. Then, we provide an efficient inception ("planting an idea in someone's mind") attack algorithm to find the optimal fake reward function within a restricted set of reward functions with dominant strategies. Importantly, our methods exploit the universal assumption of rationality to compute attacks efficiently. Thus, our work exposes a security vulnerability arising from standard game assumptions under misinformation.
Code (0)
등록된 구현이 없습니다.
Tasks
MisinformationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Inception Backdoor Attacks against Reinforcement Learning
Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks. The objectives of these attacks are twofold: induce pre-determined, adve…
Deep Reinforcement Learningreinforcement-learningReinforcement LearningThe Complexity of Markov Equilibrium in Stochastic Games
We show that computing approximate stationary Markov coarse correlated equilibria (CCE) in general-sum stochastic games is computationally intractable, even when there are two players, the game is turn-based, the discoun…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)MIND: Monge Inception Distance for Generative Models Evaluation
We propose the Monge Inception Distance (MIND), a metric for evaluating generative models that addresses key limitations of the widely adopted Fréchet Inception Distance (FID). The MIND metric leverages the sliced Wasser…
An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs
Large Language Models (LLMs) are a double-edged sword capable of generating harmful misinformation -- inadvertently, or when prompted by "jailbreak" attacks that attempt to produce malicious outputs. LLMs could, with add…
Certified Robustness of Graph Convolution Networks for Graph Classification under Topological Attacks
Graph convolution networks (GCNs) have become effective models for graph classification. Similar to many deep networks, GCNs are vulnerable to adversarial attacks on graph topology and node attributes. Recently, a numb…
General ClassificationGraph Classification