Guardauto: A Decentralized Runtime Protection System for Autonomous Driving
Guardauto: A Decentralized Runtime Protection System for Autonomous Driving
复制标题
Guardauto：自动驾驶的去中心化运行时保护系统
DOI：
10.1109/tc.2020.3018329
复制
发表时间：
2020-03
影响因子：
3.7
通讯作者：
Yang Liu
中科院分区：
文献类型：
--
作者：
Kun Cheng;Yuan Zhou;Bihuan Chen;Rui Wang;Yuebin Bai;Yang Liu
由于广泛的攻击面和缺乏运行时保护，潜在的安全和安全威胁阻碍了自动驾驶汽车的实际采用。虽然人们已经做出了一些努力来缓解一些特定的攻击，但对自动驾驶系统，即执行感知、决策和运动跟踪等功能的控制软件系统的保护工作却很少。本文提出了一种名为GuardAuto的分散式自我保护框架，以保护自动驾驶系统免受运行时威胁。首先，GuardAuto提出了一个隔离模型，将自动驾驶系统解耦，并用一组分区隔离其组件。其次，GuardAuto为每个目标组件提供了自我保护机制，它结合了不同的方法来监控目标的执行并相应地计划自适应操作。第三，GuardAuto提供本地自我保护机制之间的协作，以便在连锁故障影响多个组件的情况下识别根本原因组件。一个原型已经在开源的自动驾驶系统Autware上实现并进行了评估。结果表明，GuardAuto能够有效地缓解运行时故障和攻击，并在可接受的性能开销下保护控制系统。
Due to the broad attack surface and the lack of runtime protection, potential safety and security threats hinder the real-life adoption of autonomous vehicles. Although efforts have been made to mitigate some specific attacks, there are few works on the protection of the autonomous driving system, i.e., the control software system performing such as perception, decision making, and motion tracking. This article presents a decentralized self-protection framework called Guardauto to protect the autonomous driving system against runtime threats. First, Guardauto proposes an isolation model to decouple the autonomous driving system and isolate its components with a set of partitions. Second, Guardauto provides self-protection mechanisms for each target component, which combines different methods to monitor the target execution and plan adaption actions accordingly. Third, Guardauto provides cooperation among local self-protection mechanisms to identify the root-cause component in the case of cascading failures affecting multiple components. A prototype has been implemented and evaluated on the open-source autonomous driving system Autoware. Results show that Guardauto could effectively mitigate runtime failures and attacks, and protect the control system with acceptable performance overhead.
登录
查看更多内容
DOI：
10.1145/2517968.2517969
发表时间：
2013-11
期刊：
--
影响因子：
--
作者：
Alexandre Bouard;Benjamin Weyl;C. Eckert
通讯作者：
Alexandre Bouard;Benjamin Weyl;C. Eckert
DOI：
10.1109/tits.2014.2351612
发表时间：
2015-04-01
影响因子：
8.5
作者：
Woo, Samuel;Jo, Hyo Jin;Lee, Dong Hoon
通讯作者：
Lee, Dong Hoon
DOI：
10.1016/j.jss.2016.06.102
发表时间：
2016-11
期刊：
J. Syst. Softw.
影响因子：
--
作者：
Chung-Horng Lung;Xu Zhang;Pragash Rajeswaran
通讯作者：
Chung-Horng Lung;Xu Zhang;Pragash Rajeswaran
DOI：
10.1016/j.vehcom.2016.12.005
发表时间：
2017-10
期刊：
Veh. Commun.
影响因子：
--
作者：
Hichem Sedjelmaci;S. Senouci;Tarek Bouali
通讯作者：
Hichem Sedjelmaci;S. Senouci;Tarek Bouali
影响因子：
5.6
作者：
Alnasser, Aljawharah;Sun, Hongjian;Jian, Jing
通讯作者：
Jian, Jing