Insights on Using Deep Learning to Spoof Inertial Measurement Units for Stealthy Attacks on UAVs
Insights on Using Deep Learning to Spoof Inertial Measurement Units for Stealthy Attacks on UAVs
复制标题
DOI：
10.1109/milcom55135.2022.10017482
复制
发表时间：
2022-11
期刊：
影响因子：
--
通讯作者：
K. Kim;Denizkhan Kara;V. Paruchuri;Sibin Mohan;Greg Kimberly;Denis Osipychev;Jae H. Kim;Josh D. Eckha
中科院分区：
文献类型：
--
作者：
K. Kim;Denizkhan Kara;V. Paruchuri;Sibin Mohan;Greg Kimberly;Denis Osipychev;Jae H. Kim;Josh D. Eckha
无人驾驶飞行器（UAV）在民用和军事行动的关键任务中得到越来越多的应用。大多数无人驾驶飞行器依靠惯性测量单元（IMU）来计算飞行器姿态并跟踪飞行器位置。因此，不正确的惯性测量单元读数可能导致飞行器不稳定，甚至可能坠毁。在本文中，我们描述了一个有策略的对手如何能够引入虚假的惯性测量单元值，这些值能够使飞行器偏离其任务指定的路径，同时避开常规的异常检测机制，从而有效地对系统实施“隐蔽攻击”。我们探讨了一种深度神经网络（DNN）的可行性，该网络利用飞行器的状态信息来计算适用的惯性测量单元值以实施这种攻击。最终目标是使飞行器与其任务参数产生足够的偏差，从而损害任务的可靠性，而从操作员的角度来看，飞行器似乎仍然正常运行。
Unmanned Aerial Vehicles (UAVs) find increasing use in mission critical tasks both in civilian and military operations. Most UAVs rely on Inertial Measurement Units (IMUs) to calculate vehicle attitude and track vehicle position. Therefore, an incorrect IMU reading can cause a vehicle to destabilize, and possibly even crash. In this paper, we describe how a strategic adversary might be able to introduce spurious IMU values that can deviate a vehicle from its mission-specified path while at the same time evade customary anomaly detection mechanisms, thereby effectively perpetuating a “stealthy attack” on the system. We explore the feasibility of a Deep Neural Network (DNN) that uses a vehicle's state information to calculate the applicable IMU values to perpetrate such an attack. The eventual goal is to cause a vehicle to perturb enough from its mission parameters to compromise mission reliability, while, from the operator's perspective, the vehicle still appears to be operating normally.