arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.11070cs.LGcs.AIcs.CR
收藏

使用因果建模与树搜索的CAGE-2最优防御者策略

Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search

KTH Royal Institute of Technology(KTH皇家理工学院);Siemens Technology(西门子技术)

Kim Hammar, Neil Dhir, Rolf Stadler

AI总结:

本文提出C-POMCP方法,通过因果建模缩减搜索空间并结合在线树搜索,为CAGE-2自主网络防御生成可证明最优策略,在有效性上达到最先进水平且计算效率提升两个数量级。

摘要:

CAGE-2挑战被视为比较自主网络防御方法的标准基准。当前针对该基准评估的最先进方法基于无模型(离线)强化学习,无法提供可证明最优的防御者策略。我们针对这一局限,提出了CAGE-2的形式化(因果)模型,以及一种生成可证明最优防御者策略的方法,我们称之为因果部分可观测蒙特卡洛规划(C-POMCP)。该方法具有两个关键特性。第一,它融入了目标系统的因果结构,即系统变量之间的因果关系。该结构能够显著缩减防御者策略的搜索空间。第二,它是一种在线方法,在每个时间步通过树搜索更新防御者策略。针对CAGE-2基准的评估表明,C-POMCP在有效性方面达到了最先进性能,并且计算时间比最接近的竞争方法高效两个数量级。

英文摘要:

The CAGE-2 challenge is considered a standard benchmark to compare methods for autonomous cyber defense. Current state-of-the-art methods evaluated against this benchmark are based on model-free (offline) reinforcement learning, which does not provide provably optimal defender strategies. We address this limitation and present a formal (causal) model of CAGE-2 together with a method that produces a provably optimal defender strategy, which we call Causal Partially Observable Monte-Carlo Planning (C-POMCP). It has two key properties. First, it incorporates the causal structure of the target system, i.e., the causal relationships among the system variables. This structure allows for a significant reduction of the search space of defender strategies. Second, it is an online method that updates the defender strategy at each time step via tree search. Evaluations against the CAGE-2 benchmark show that C-POMCP achieves state-of-the-art performance with respect to effectiveness and is two orders of magnitude more efficient in computing time than the closest competitor method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑