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 2408.08433cs.CR
收藏

基于分层联邦学习的车载网络安全鲁棒多阶段入侵检测系统

A Robust Multi-Stage Intrusion Detection System for In-Vehicle Network Security using Hierarchical Federated Learning

Muzun Althunayyan, Amir Javed, Omer Rana

AI总结:

针对CAN总线车载网络易受攻击的问题,提出结合ANN与LSTM自编码器的多阶段轻量入侵检测系统,基于分层联邦学习部署,在已知和新型攻击检测上均取得优异性能且误报率极低。

摘要:

随着网联汽车和自动驾驶汽车的普及,控制器局域网(Controller Area Network,CAN)总线凭借其速度和效率,已成为车载网络的主流通信标准。然而,CAN总线缺乏身份认证、加密等基础安全机制,极易遭受网络攻击。为保障车载安全,入侵检测系统(intrusion detection systems,IDSs)需既能检测已知攻击,又能对新型未知攻击提供鲁棒防御,同时还需保持轻量级以满足实际部署需求。\n此前的研究仅依赖CAN ID特征,或采用需手动提取特征的传统机器学习(machine learning,ML)方法,这些方法忽略了其他可利用的特征,难以适配新型未知攻击变体,进而削弱了安全性。本文提出一种前沿的新型轻量级车载入侵检测系统,采用深度学习(deep learning,DL)算法以解决上述局限。\n该入侵检测系统采用多阶段架构:第一阶段使用人工神经网络(artificial neural network,ANN)检测已知攻击,第二阶段使用长短期记忆(Long Short-Term Memory,LSTM)自编码器检测新型未知攻击。为理解和分析多样化的驾驶行为、用最新攻击模式更新模型,同时保护数据隐私,我们提出了一个理论框架,将该入侵检测系统部署在分层联邦学习(hierarchical federated learning,H-FL)环境中。\n实验结果表明,该入侵检测系统对已知攻击的F1值超过0.99,对新型攻击的F1值超过0.95,检测率达99.99%;此外,其误报率(false alarm rate,FAR)极低,仅为0.016%,最大程度减少了误报。尽管采用了以识别复杂攻击和零日攻击见长的深度学习算法,该入侵检测系统仍保持轻量级特性,确保了其在实际场景中的部署可行性。

英文摘要:

As connected and autonomous vehicles proliferate, the Controller Area Network (CAN) bus has become the predominant communication standard for in-vehicle networks due to its speed and efficiency. However, the CAN bus lacks basic security measures such as authentication and encryption, making it highly vulnerable to cyberattacks. To ensure in-vehicle security, intrusion detection systems (IDSs) must detect seen attacks and provide a robust defense against new, unseen attacks while remaining lightweight for practical deployment. Previous work has relied solely on the CAN ID feature or has used traditional machine learning (ML) approaches with manual feature extraction. These approaches overlook other exploitable features, making it challenging to adapt to new unseen attack variants and compromising security. This paper introduces a cutting-edge, novel, lightweight, in-vehicle, IDS-leveraging, deep learning (DL) algorithm to address these limitations. The proposed IDS employs a multi-stage approach: an artificial neural network (ANN) in the first stage to detect seen attacks, and a Long Short-Term Memory (LSTM) autoencoder in the second stage to detect new, unseen attacks. To understand and analyze diverse driving behaviors, update the model with the latest attack patterns, and preserve data privacy, we propose a theoretical framework to deploy our IDS in a hierarchical federated learning (H-FL) environment. Experimental results demonstrate that our IDS achieves an F1-score exceeding 0.99 for seen attacks and exceeding 0.95 for novel attacks, with a detection rate of 99.99%. Additionally, the false alarm rate (FAR) is exceptionally low at 0.016%, minimizing false alarms. Despite using DL algorithms known for their effectiveness in identifying sophisticated and zero-day attacks, the IDS remains lightweight, ensuring its feasibility for real-world deployment.

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。

↑