Few-Shot Backdoor Attacks on Visual Object Tracking
This reveals a vulnerability in VOT models used in mission-critical applications like autonomous driving, posing a security risk, but it is incremental as it applies known backdoor attack concepts to a new domain.
The paper tackles the security threat of backdoor attacks in visual object tracking (VOT) by proposing a few-shot backdoor attack (FSBA) that implants hidden backdoors into models, causing them to lose track of specific objects with triggers in few frames, and it significantly degrades state-of-the-art tracker performance while resisting defenses.
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. Specifically, we propose a simple yet effective few-shot backdoor attack (FSBA) that optimizes two losses alternately: 1) a \emph{feature loss} defined in the hidden feature space, and 2) the standard \emph{tracking loss}. We show that, once the backdoor is embedded into the target model by our FSBA, it can trick the model to lose track of specific objects even when the \emph{trigger} only appears in one or a few frames. We examine our attack in both digital and physical-world settings and show that it can significantly degrade the performance of state-of-the-art VOT trackers. We also show that our attack is resistant to potential defenses, highlighting the vulnerability of VOT models to potential backdoor attacks.