Few-Shot Backdoor Attacks on Visual Object Tracking. (arXiv:2201.13178v2 [cs.CV] UPDATED)

Web: http://arxiv.org/abs/2201.13178

Visual object tracking (VOT) has been widely adopted in mission-critical
applications, such as autonomous driving and intelligent surveillance systems.
In current practice, third-party resources such as datasets, backbone networks,
and training platforms are frequently used to train high-performance VOT
models. Whilst these resources bring certain convenience, they also introduce
new security threats into VOT models. In this paper, we reveal such a threat
where an adversary can easily implant hidden backdoors into VOT models by
tempering with the training process. …

arxiv attacks cv on tracking