arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.08182cs.CRcs.AIcs.LG
收藏

基于深度Q网络和系统划分的入侵响应系统

An Intrusion Response System utilizing Deep Q-Networks and System Partitions

University of Rome Tor Vergata(罗马第二大学);Sapienza University of Rome(罗马第一大学);Roma Tre University(罗马第三大学);Mississippi State University(密西西比州立大学)

Valeria Cardellini, Emiliano Casalicchio, Stefano Iannucci, Matteo Lucantonio, Sudip Mittal, Damodar Panigrahi, Andrea Silvi

摘要:

入侵响应是一个相对较新的研究领域。最近创建入侵响应系统(IRS)的方法使用强化学习(RL)作为主要技术,用于选择最佳或接近最佳的适当对策,以阻止或减轻正在进行的攻击。然而,他们中的大多数没有考虑到系统可以随时间变化的事实,或者换句话说,系统表现出非平稳行为。此外,有状态的方法,如基于RL的方法,由于状态空间随受保护系统的大小呈指数增长而遭受维数灾难。在本文中,我们介绍和开发了一个IRS软件原型,命名为IRS分区。它利用受保护系统和Deep Q-Networks的分区,通过支持多代理制定来解决维度灾难。此外,它利用迁移学习来跟踪非平稳系统的演化。

英文摘要:

Intrusion Response is a relatively new field of research. Recent approaches for the creation of Intrusion Response Systems (IRSs) use Reinforcement Learning (RL) as a primary technique for the optimal or near-optimal selection of the proper countermeasure to take in order to stop or mitigate an ongoing attack. However, most of them do not consider the fact that systems can change over time or, in other words, that systems exhibit a non-stationary behavior. Furthermore, stateful approaches, such as those based on RL, suffer the curse of dimensionality, due to a state space growing exponentially with the size of the protected system. In this paper, we introduce and develop an IRS software prototype, named irs-partition. It leverages the partitioning of the protected system and Deep Q-Networks to address the curse of dimensionality by supporting a multi-agent formulation. Furthermore, it exploits transfer learning to follow the evolution of non-stationary systems.

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。

↑