Newest papers

Adaptive Cyber-Defense for Evolving Attacker Capabilities using Reinforcement Learning and Behavior Trees

Nicholas Potteiger, Ankita Samaddar, Xenofon Koutsoukos · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.25420 · cited by 0 works (OpenAlex) · open-access PDF

Korean

CAGE 도전 시나리오 2 (CC2)에서 배운 방어 정책을 적응하는 문제를 연구하는 이 작품에서는 CAGE 도전 시나리오 2 (CC2)에서 배운 방어 정책을 CAGE 도전 시나리오 2 (CC2)에서 적응하는 문제를 연구합니다. 그러나 기존의 접근 방식은 공격자의 능력이 진화하고 새로운 공격 전략을 활용하는 효과적인 공격 전략은 처음에는 알려지지지 않으며, 따라서 방어 적응이 발생하기 전에 공격자의 정책을 배우는 문제를 연구합니다. 이 문제를 해결하기 위해 우리는 새로운 공격자 기능과 RBT 실행에 대한 새로운 노드 라인에 대한 진보 기반 보상 기능과 조건을 보여주는 효과적인 공격자 전략을 정의하기 위해 새로운 공격자 행동을 사용하여 공격자 행동에 대한 새로운 공격자 행동

Machine translation (Meta M2M100); the English original follows.

Abstract

Autonomous cyber-defense agents trained using reinforcement learning (RL) are increasingly adopted for defending enterprise computer networks. However, existing approaches may become brittle as attacker capabilities evolve and enable new attack strategies. In this work, we study the problem of adapting defender policies learned in CAGE Challenge Scenario 2 (CC2), a benchmark enterprise network defense scenario, to an extended network scenario with new attacker capabilities represented by new attacker actions. Effective attack strategies that leverage new actions are initially unknown, and therefore attacker policies must be learned before defender adaptation can occur. To address this challenge, we develop adversarial RL (ARL) with behavior trees (ARLBT), which uses reward behavior trees (RBTs) to define progression-based reward functions and condition attacker policies on RBT execution. The proposed RBT incorporates the new attacker actions into structured attack strategies while leveraging parallel execution to generate rewards across multiple network nodes simultaneously. We evaluate ARLBT for learning attacker policies against two baseline defender policies across network scenarios with different sets of new attacker actions and compare against multiple attacker baselines. The results demonstrate that ARLBT improves attacker success compared to ARL using the original CC2 reward function and that conditioning policies on RBT execution can improve sample efficiency. We further show that defender policies can be adapted against the learned attackers, improving robustness to attacks that leverage new attacker actions.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Reinforcement learning, Computer science, Adversarial system, Leverage (statistics), Computer security, Robustness (evolution)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange