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 2406.00707cs.RO
收藏

QUADFormer:基于学习的四旋翼无人机网络攻击检测

QUADFormer: Learning-based Detection of Cyber Attacks in Quadrotor UAVs

Southern University of Science and Technology(南方科技大学);Hong Kong University of Science and Technology(香港科技大学)

Pengyu Wang, Zhaohua Yang, Nachuan Yang, Zikai Wang, Jialu Li, Fan Zhang, Chaoqun Wang, Jiankun Wang, Max Q. -H. Meng, Ling Shi

AI总结:

针对四旋翼无人机在非高斯噪声和高非线性动力学下攻击检测困难的问题,本文提出基于 Transformer 的 QUADFormer 框架,通过残差生成与相关性差异学习实现高精度攻击检测,并在仿真和真实实验中验证了其优越性。

摘要:

安全关键的智能信息物理系统(如四旋翼无人机(UAV))容易受到不同类型的网络攻击,缺乏及时准确的攻击检测可能导致严重后果。当无人机进行大规模户外机动飞行时,其系统构成高度非线性动力学,并包含非高斯噪声。因此,常用的基于传统统计的方法和新兴的基于学习的攻击检测方法均无法产生令人满意的结果。针对上述挑战,我们提出了 QUADFormer,一种新颖的基于 Transformer 架构的四旋翼无人机攻击检测框架。该框架包含一个残差生成器,用于生成对异常敏感的残差序列。随后,该序列被输入到具有相关性差异的 Transformer 结构中,以专门学习其统计特征,用于分类和攻击检测。最后,我们设计了一个警报模块,以确保无人机在攻击条件下安全执行任务。我们进行了大量仿真和真实世界实验,结果表明,与许多最先进的方法相比,我们的方法取得了优越的检测性能。

英文摘要:

Safety-critical intelligent cyber-physical systems, such as quadrotor unmanned aerial vehicles (UAVs), are vulnerable to different types of cyber attacks, and the absence of timely and accurate attack detection can lead to severe consequences. When UAVs are engaged in large outdoor maneuvering flights, their system constitutes highly nonlinear dynamics that include non-Gaussian noises. Therefore, the commonly employed traditional statistics-based and emerging learning-based attack detection methods do not yield satisfactory results. In response to the above challenges, we propose QUADFormer, a novel Quadrotor UAV Attack Detection framework with transFormer-based architecture. This framework includes a residue generator designed to generate a residue sequence sensitive to anomalies. Subsequently, this sequence is fed into a transformer structure with disparity in correlation to specifically learn its statistical characteristics for the purpose of classification and attack detection. Finally, we design an alert module to ensure the safe execution of tasks by UAVs under attack conditions. We conduct extensive simulations and real-world experiments, and the results show that our method has achieved superior detection performance compared with many state-of-the-art methods.

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。

↑