攻击多目标追踪的查询传播机制，让跟踪器误判或丢失目标。
Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation
- 通过制造虚假查询耗尽追踪器预算，强制中断真实轨迹。
- 破坏查询更新的记忆关联，使已匹配目标身份失效。
- 可模拟物理世界攻击，对先进追踪器效果显著。
基于查询传播（TBP）的多目标追踪方法通过端到端架构实现长时序建模，但其依赖查询传播的特性引入了新型安全漏洞。本文提出FADE攻击框架，针对TBP核心机制设计两种策略：(i) 时间查询泛滥——生成具时间一致性的虚假查询，耗尽追踪器有限的查询预算，迫使有效轨迹终止；(ii) 时间记忆污染——通过状态去相关与特征身份擦除，直接攻击查询更新器的记忆结构，切断时间关联。此外，我们构建可微分流水线，结合先进感知传感器欺骗仿真，优化攻击在真实场景中的可实现性。在MOT17与MOT20基准上的实验表明，FADE对当前主流TBP追踪器具有极强破坏力，导致大量身份切换与轨迹中断。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。