arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.02445cs.CRcs.AIcs.LG
收藏

工业控制系统的自主攻击缓解

Autonomous Attack Mitigation for Industrial Control Systems

Stanford University(斯坦福大学);Johns Hopkins University Applied Physics Lab(约翰斯·霍普金斯大学应用物理实验室)

John Mern, Kyle Hatch, Ryan Silva, Cameron Hickert, Tamim Sookoor, Mykel J. Kochenderfer

摘要:

保护计算机网络免受网络攻击需要及时响应警报和威胁情报。关于如何响应的决策涉及基于不完美的妥协指标协调多个节点的行动,同时最大限度地减少对网络运营的中断。目前,剧本用于自动化响应过程的部分,但通常将复杂的决策留给人类分析师。在这项工作中,我们提出了一个深度的强化学习方法,在大型工业控制网络的自主响应和恢复。我们提出了一种基于注意力的神经架构,该架构对受保护的网络的大小是灵活的。为了训练和评估自主防御Agent,我们提出了一个适合强化学习的工业控制网络仿真环境。实验表明,学习代理可以有效地减轻高级攻击,在执行前几个月内几乎没有可观察到的信号。所提出的深度强化学习方法在模拟中优于完全自动化的剧本方法,采取更少的破坏性行动,同时还保护网络上的更多节点。学习的策略也比剧本方法对攻击者行为的变化更鲁棒。

英文摘要:

Defending computer networks from cyber attack requires timely responses to alerts and threat intelligence. Decisions about how to respond involve coordinating actions across multiple nodes based on imperfect indicators of compromise while minimizing disruptions to network operations. Currently, playbooks are used to automate portions of a response process, but often leave complex decision-making to a human analyst. In this work, we present a deep reinforcement learning approach to autonomous response and recovery in large industrial control networks. We propose an attention-based neural architecture that is flexible to the size of the network under protection. To train and evaluate the autonomous defender agent, we present an industrial control network simulation environment suitable for reinforcement learning. Experiments show that the learned agent can effectively mitigate advanced attacks that progress with few observable signals over several months before execution. The proposed deep reinforcement learning approach outperforms a fully automated playbook method in simulation, taking less disruptive actions while also defending more nodes on the network. The learned policy is also more robust to changes in attacker behavior than playbook approaches.

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。

↑