# Inception: Efficiently Computable Misinformation Attacks on Markov Games

arXiv: https://arxiv.org/abs/2406.17114 · HTML: https://mlsanity.com/paper/2406.17114/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 8 of 8)

- [Adversarial Policies: Attacking Deep Reinforcement Learning](https://mlsanity.com/paper/1905.10615/) (2019)
- [Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning](https://mlsanity.com/paper/2003.12909/) (2020)
- [Policy Poisoning in Batch Reinforcement Learning and Control](https://mlsanity.com/paper/1910.05821/) (2019)
- [Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks](https://mlsanity.com/paper/2011.10824/) (2020)
- [Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning](https://mlsanity.com/paper/2208.13663/) (2022)
- [Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2206.01888/) (2022)
- [Fast Planning in Stochastic Games](https://mlsanity.com/paper/1301.3867/) (2013)
- [Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value](https://mlsanity.com/paper/2311.00582/) (2023)

## Built on by (most cited first, 1 of 1)

- [When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs](https://mlsanity.com/paper/2604.10062/) (2026)

## Abstract (arXiv)

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.