# Omniscient Attacker in Stochastic Security Games with Interdependent Nodes

arXiv: https://arxiv.org/abs/2512.04561 · HTML: https://mlsanity.com/paper/2512.04561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Builds on (most cited first, 5 of 5)

- [Strategizing against No-regret Learners](https://mlsanity.com/paper/1909.13861/) (2019)
- [Model-Based Opponent Modeling](https://mlsanity.com/paper/2108.01843/) (2021)
- [Intelligent Players in a Fictitious Play Framework](https://mlsanity.com/paper/2110.05939/) (2021)
- [Strategizing against Q-learners: A Control-theoretical Approach](https://mlsanity.com/paper/2403.08906/) (2024)
- [Rationality of Learning Algorithms in Repeated Normal-Form Games](https://mlsanity.com/paper/2402.08747/) (2024)

## Abstract (arXiv)

The adoption of reinforcement learning for critical infrastructure defense introduces a vulnerability where sophisticated attackers can strategically exploit the defense algorithm's learning dynamics. While prior work addresses this vulnerability in the context of repeated normal-form games, its extension to the stochastic games remains an open research gap. We close this gap by examining stochastic security games between an RL defender and an omniscient attacker, utilizing a tractable linear influence network model. To overcome the structural limitations of prior methods, we propose and apply neuro-dynamic programming. Our experimental results demonstrate that the omniscient attacker can significantly outperform a naive defender, highlighting the critical vulnerability introduced by the learning dynamics and the effectiveness of the proposed strategy.