In a spoofing attack, an attacker impersonates a legitimate user to access or
modify data belonging to the latter. Typical approaches for spoofing detection
in the physical layer declare an attack when a change is observed in certain
channel features, such as the received signal strength (RSS) measured by
spatially distributed receivers. However, since channels change over time, for
example due to user movement, such approaches are impractical. To sidestep this
limitation, this paper proposes a scheme that combines the decisions of a
position-change detector based on a deep neural network to distinguish spoofing
from movement. Building upon community detection on graphs, the sequence of
received frames is partitioned into subsequences to detect concurrent
transmissions from distinct locations. The scheme can be easily deployed in
practice since it just involves collecting a small dataset of measurements at a
few tens of locations that need not even be computed or recorded. The scheme is
evaluated on real data collected for this purpose.

该论文提出了一种方案，结合基于深度神经网络的位置改变检测器的决策，以区分伪造行为和移动，并通过图上的社区检测方法将接收到的帧序列分割为子序列，以检测不同位置的同时传输。该方案可以轻松部署在实践中，只需在少量位置收集一小部分测量数据，甚至不需要计算或记录。该方案在为此目的收集的真实数据上进行了评估。

在物理层中具有对用户移动鲁棒性的欺骗攻击检测

Spoofing Attack Detection in the Physical Layer with Robustness to User  Movement

The safety and security of the passengers in vehicles in the face of cyber
attacks is a key element in the automotive industry, especially with the
emergence of the Advanced Driver Assistance Systems (ADAS) and the vast
improvement in Autonomous Vehicles (AVs). Such platforms use various sensors,
including cameras, LiDAR and mmWave radar. These sensors themselves may present
a potential security hazard if exploited by an attacker.
In this paper we propose a system to attack an automotive FMCW mmWave radar,
that uses fast chirp modulation. Using a single rogue radar, our attack system
is capable of spoofing the distance and velocity measured by the victim vehicle
simultaneously, presenting phantom measurements coherent with the laws of
physics governing vehicle motion. The attacking radar controls the delay in
order to spoof its distance, and uses phase compensation and control in order
to spoof its velocity. After developing the attack theory, we demonstrate the
spoofing attack by building a proof-of-concept hardware-based system, using a
Software Defined Radio. We successfully demonstrate two real world scenarios in
which the victim radar is spoofed to detect either a phantom emergency stop or
a phantom acceleration, while measuring coherent range and velocity. We also
discuss several countermeasures to the attack, in order to propose ways to
mitigate the described attack.

本文提出了一种攻击自动驾驶雷达的系统，使用单一的恶意雷达伪造车辆测量并同时伪造相干的物理测量结果，同时还讨论了一些抵御该攻击的对策。