Abstract
Recent Tracking-by-Query-Propagation (TBP) methods have advanced Multi-Object Tracking (MOT) by enabling end-to-end (E2E) pipelines with long-range temporal modeling. However, this reliance on query propagation introduces unexplored architectural vulnerabilities to adversarial attacks. We present FADE, a novel attack framework designed to exploit these specific vulnerabilities. FADE employs two attack strategies targeting core TBP mechanisms: (i) Temporal Query Flooding: Generates spurious temporally consistent track queries to exhaust the tracker's limited query budget, forcing it to terminate valid tracks. (ii) Temporal Memory Corruption: Directly attacks the query updater's memory by severing temporal links via state de-correlation and erasing the learned feature identity of matched tracks. Furthermore, we introduce a differentiable pipeline to optimize these attacks for physical-world realizability by leveraging simulations of advanced perception sensor spoofing. Experiments on MOT17 and MOT20 benchmarks demonstrate that FADE is highly effective against state-of-the-art TBP trackers, causing significant identity switches and track terminations.
Abstract (translated)
近期，基于查询传播（TBP）的方法通过实现具备长时域建模能力的端到端（E2E）管道，推动了多目标跟踪（MOT）的发展。然而，这种对查询传播的依赖引入了对抗攻击中尚未被探索的架构漏洞。本文提出FADE，一种旨在利用这些特定漏洞的新型攻击框架。FADE采用两种针对核心TBP机制的攻击策略：（i）时序查询洪泛：生成虚假的时序一致跟踪查询，以耗尽跟踪器的有限查询预算，迫使其终止有效跟踪；（ii）时序记忆污染：通过状态去相关切断时序关联，并擦除已匹配跟踪的已学习特征身份，直接攻击查询更新器的记忆模块。此外，我们引入了一种可微分管道，通过利用高级感知传感器欺骗的模拟来优化这些攻击，以实现物理世界可实现性。在MOT17和MOT20基准测试上的实验表明，FADE对最先进的TBP跟踪器具有高度攻击效果，导致显著的身份切换和跟踪终止。
URL
https://arxiv.org/abs/2604.00452
