Metraipolis › archive › dc_df650c4ad8dc

TrackFlood: Relocating Latency Attacks from NMS-Free Detectors to Real-Time Trackers — arXiv:2609.33948

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33948
License (as archived)
CC0-1.0
Archived
2026-10-07T22:34:43.758Z
SHA-256 of the archived text
d2c0a8604f095cde0db3413632b86794c653af6a797780bce0bbf6f5d27e0345
Stable URL of this page
https://metraipolis.com/documento/dc_df650c4ad8dc

How to cite

TrackFlood: Relocating Latency Attacks from NMS-Free Detectors to Real-Time Trackers — arXiv:2609.33948 — arXiv (en), https://arxiv.org/abs/2609.33948 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df650c4ad8dc (Metraipolis archive dc_df650c4ad8dc, sha256 d2c0a8604f095cde0db3413632b86794c653af6a797780bce0bbf6f5d27e0345)
BibTeX
@misc{dcdf650c4ad8dc,
  title = {TrackFlood: Relocating Latency Attacks from NMS-Free Detectors to Real-Time Trackers — arXiv:2609.33948},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33948},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df650c4ad8dc; sha256 d2c0a8604f095cde0db3413632b86794c653af6a797780bce0bbf6f5d27e0345},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33948. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We consider latency attacks on object detectors, where the attacker's goal is not to corrupt a prediction but to make the system fail to respond in time, targeting real-time applications such as autonomous driving. Modern object detectors eliminate Non-Maximum Suppression (NMS) through one-to-one assignment or set prediction, removing the classical detector-side latency bottleneck exploited by prior latency (``sponge'') attacks. We show that NMS-free does not mean latency-robust: this architectural change does not eliminate the attack surface but relocates it downstream to multi-object tracking, whose data-association cost remains content dependent. We present \emph{TrackFlood}, a unified white-box overload attack against NMS-free detect-then-track pipelines spanning both one-to-one detectors (YOLOv10 and YOLO26) and query-based detectors (RT-DETR). TrackFlood recovers differentiable confidence tensors and optimizes perturbations that flood the tracker with spatially distributed phantom detections while leaving detector inference unchanged. Evaluated entirely on an NVIDIA Jetson AGX Orin (TensorRT FP16), detector latency remains essentially constant, whereas tracker latency increases substantially. At a standard imperceptible budget ($L_\infty{=}8/255$), a universal perturbation produces clearly measurable tracker overload but only modest end-to-end slowdown, without deadline misses for the association-dominated trackers; a separate higher-budget stress test drives severe end-to-end slowdowns and sustained deadline misses. We further evaluate a lightweight, architecture-agnostic bounded-admission layer that caps the tracker workload and largely restores end-to-end latency, at a non-trivial cost in admitted clean detections. Our results demonstrate that evaluating NMS-free perception systems requires considering downstream tracking and end-to-end timing, not detector inference alone.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.33948 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T22:13:03.704Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).