BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks

Multi-object tracking (MOT) aims to construct moving trajectories for objects, and modern multi-object trackers mainly utilize the tracking-by-detection methodology. Initial approaches to MOT attacks primarily aimed to degrade the detection quality of the frames under attack, thereby reducing accuracy only in those specific frames, highlighting a lack of textitefficiency. To improve efficiency, recent advancements manipulate object positions to cause persistent identity (ID) switches during the association phase, even after the attack ends within a few frames. However, these position-manipulating attacks have inherent limitations, as they can be easily counteracted by adjusting distance-related parameters in the association phase, revealing a lack of textitrobustness. In this paper, we present textsfBankTweak, a novel adversarial attack designed for MOT trackers, which features efficiency and robustness. textsfBankTweak focuses on the feature extractor in the association phase and reveals vulnerability in the Hungarian matching method used by feature-based MOT systems. Exploiting the vulnerability, textsfBankTweak induces persistent ID switches (addressing textitefficiency) even after the attack ends by strategically injecting altered features into the feature banks without modifying object positions (addressing textitrobustness). To demonstrate the applicability, we apply textsfBankTweak to three multi-object trackers (DeepSORT, StrongSORT, and MOTDT) with one-stage, two-stage, anchor-free, and transformer detectors. Extensive experiments on the MOT17 and MOT20 datasets show that our method substantially surpasses existing attacks, exposing the vulnerability of the tracking-by-detection framework to textsfBankTweak.