# Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning

arXiv: https://arxiv.org/abs/1906.08805 · HTML: https://mlsanity.com/paper/1906.08805/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2019.

## Built on by (most cited first, 12 of 12)

- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Preference Poisoning Attacks on Reward Model Learning](https://mlsanity.com/paper/2402.01920/) (2024)
- [Policy Space Response Oracles: A Survey](https://mlsanity.com/paper/2403.02227/) (2024)
- [That Escalated Quickly: An ML Framework for Alert Prioritization](https://mlsanity.com/paper/2302.06648/) (2023)
- [SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity](https://mlsanity.com/paper/2602.08690/) (2026)
- [RADAMS: Resilient and Adaptive Alert and Attention Management Strategy against Informational Denial-of-Service (IDoS) Attacks](https://mlsanity.com/paper/2111.03463/) (2021)
- [Beyond Rewards in Reinforcement Learning for Cyber Defence](https://mlsanity.com/paper/2602.04809/) (2026)
- [Multi-Agent Reinforcement Learning for Assessing False-Data Injection Attacks on Transportation Networks](https://mlsanity.com/paper/2312.14625/) (2023)
- [Advancing LLM-Based Security Automation with Customized Group Relative Policy Optimization for Zero-Touch Networks](https://mlsanity.com/paper/2512.09485/) (2025)
- [Principled Data-Driven Decision Support for Cyber-Forensic Investigations](https://mlsanity.com/paper/2211.13345/) (2022)
- [PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense](https://mlsanity.com/paper/2508.19488/) (2025)
- [Adversarial Reinforcement Learning for Detecting False Data Injection Attacks in Vehicular Routing](https://mlsanity.com/paper/2603.11433/) (2026)

## Abstract (arXiv)

Detection of malicious behavior is a fundamental problem in security. One of the major challenges in using detection systems in practice is in dealing with an overwhelming number of alerts that are triggered by normal behavior (the so-called false positives), obscuring alerts resulting from actual malicious activity. While numerous methods for reducing the scope of this issue have been proposed, ultimately one must still decide how to prioritize which alerts to investigate, and most existing prioritization methods are heuristic, for example, based on suspiciousness or priority scores. We introduce a novel approach for computing a policy for prioritizing alerts using adversarial reinforcement learning. Our approach assumes that the attackers know the full state of the detection system and dynamically choose an optimal attack as a function of this state, as well as of the alert prioritization policy. The first step of our approach is to capture the interaction between the defender and attacker in a game theoretic model. To tackle the computational complexity of solving this game to obtain a dynamic stochastic alert prioritization policy, we propose an adversarial reinforcement learning framework. In this framework, we use neural reinforcement learning to compute best response policies for both the defender and the adversary to an arbitrary stochastic policy of the other. We then use these in a double-oracle framework to obtain an approximate equilibrium of the game, which in turn yields a robust stochastic policy for the defender. Extensive experiments using case studies in fraud and intrusion detection demonstrate that our approach is effective in creating robust alert prioritization policies.