arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.08141cs.CR
收藏

IoTWarden:一种基于深度强化学习的实时防御系统,用于缓解触发-动作式物联网攻击

IoTWarden: A Deep Reinforcement Learning Based Real-time Defense System to Mitigate Trigger-action IoT Attacks

Md Morshed Alam, Israt Jahan, Weichao Wang

AI总结:

本文提出IoTWarden,一种基于深度强化学习和深度Q网络的实时防御系统,通过定义奖励函数学习最优防御策略,以低计算开销有效识别并缓解触发-动作式物联网中的远程注入攻击。

摘要:

在触发-动作式物联网平台中,物联网设备向物联网集线器报告事件条件,通知其网络状态,并让集线器根据规则引擎中定义为规则的功能依赖关系在其他物联网设备中调用动作。这些功能依赖关系形成了一条交互链,有助于自动化网络任务。攻击者利用这条链向物联网集线器报告虚假事件条件,并对智能环境执行远程注入攻击,以间接控制目标物联网设备。现有的防御工作通常依赖于对物联网应用进行静态分析来开发基于规则的异常检测机制。文献中也有基于机器学习的防御机制,利用物理事件指纹来确定物联网网络中的异常。然而,这些方法在面对复杂攻击时往往表现出较长的响应时间和缺乏适应性。在本文中,我们提出构建一个基于深度强化学习的实时防御系统来应对注入攻击。我们为防御者定义了奖励函数,并实现了一种基于深度Q网络的方法来识别最优防御策略。我们的实验表明,所提出的机制能够以合理的计算开销有效且准确地识别和防御注入攻击。

英文摘要:

In trigger-action IoT platforms, IoT devices report event conditions to IoT hubs notifying their cyber states and let the hubs invoke actions in other IoT devices based on functional dependencies defined as rules in a rule engine. These functional dependencies create a chain of interactions that help automate network tasks. Adversaries exploit this chain to report fake event conditions to IoT hubs and perform remote injection attacks upon a smart environment to indirectly control targeted IoT devices. Existing defense efforts usually depend on static analysis over IoT apps to develop rule-based anomaly detection mechanisms. We also see ML-based defense mechanisms in the literature that harness physical event fingerprints to determine anomalies in an IoT network. However, these methods often demonstrate long response time and lack of adaptability when facing complicated attacks. In this paper, we propose to build a deep reinforcement learning based real-time defense system for injection attacks. We define the reward functions for defenders and implement a deep Q-network based approach to identify the optimal defense policy. Our experiments show that the proposed mechanism can effectively and accurately identify and defend against injection attacks with reasonable computation overhead.

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。

↑