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 2602.05121eess.SYcs.ROcs.SY
收藏

针对机器人系统神经网络控制器的木马攻击

Trojan Attacks on Neural Network Controllers for Robotic Systems

Concordia University(康科德大学);Concordia Institute for Information Systems Engineering(康科德信息系统工程研究所);Fonds de recherche du Québec – Nature et Technologies(魁北克自然与技术研究基金);National Cybersecurity Consortium(国家网络安全联盟)

Farbod Younesi, Walter Lucia, Amr Youssef

AI总结:

针对机器人神经网络控制器,设计轻量级并行木马网络,在特定触发条件下篡改控制指令,通过仿真验证攻击有效性。

摘要:

神经网络控制器越来越多地应用于机器人系统中,用于轨迹跟踪和姿态稳定等任务。然而,它们对可能不可信的训练流程或供应链的依赖引入了显著的安全漏洞。本文以差速驱动移动机器人平台为案例,研究针对神经控制器的后门(木马)攻击。具体来说,假设机器人的跟踪控制器实现为神经网络,我们设计了一个轻量级的并行木马网络,可以嵌入到控制器中。该恶意模块在正常操作期间保持休眠,但在检测到由机器人姿态和目标参数定义的高度特定触发条件时,会破坏主控制器的轮速命令,导致不良且可能不安全的机器人行为。我们提供了所提出的木马网络的概念验证实现,并通过两种不同攻击场景下的仿真进行了验证。结果证实了所提出攻击的有效性,并表明基于神经网络的机器人控制系统面临潜在的关键安全威胁。

英文摘要:

Neural network controllers are increasingly deployed in robotic systems for tasks such as trajectory tracking and pose stabilization. However, their reliance on potentially untrusted training pipelines or supply chains introduces significant security vulnerabilities. This paper investigates backdoor (Trojan) attacks against neural controllers, using a differential-drive mobile robot platform as a case study. In particular, assuming that the robot's tracking controller is implemented as a neural network, we design a lightweight, parallel Trojan network that can be embedded within the controller. This malicious module remains dormant during normal operation but, upon detecting a highly specific trigger condition defined by the robot's pose and goal parameters, compromises the primary controller's wheel velocity commands, resulting in undesired and potentially unsafe robot behaviours. We provide a proof-of-concept implementation of the proposed Trojan network, which is validated through simulation under two different attack scenarios. The results confirm the effectiveness of the proposed attack and demonstrate that neural network-based robotic control systems are subject to potentially critical security threats.

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。

↑