AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Out of Sight, Out of Track: Adversarial Attacks on Propagation-based Multi-Object Trackers via Query State Manipulation

Halima Bouzidi, Haoyu Liu, Yonatan Achamyeleh, Praneetsai Iddamsetty, Mohammad Al Faruque

CVPR 2026 · Adversarial robustness and security › Attacks on text and graphs · approach: Physical adversarial patches and camouflage · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Cost and Siphon losses to flooding loss in TQF (ablation)FADE-TQF on CO-MOT · MOT17HOTA under attack: 40.25 -> 37.26Improved
add L_Cost to TQF (ablation)FADE-TQF on Samba · MOT17HOTA under attack: 53.14 -> 45.53Improved
add L_Siphon to TQF (ablation)FADE-TQF on Samba · MOT17HOTA under attack: 44.96 -> 45.53Hurt
add L_Siphon to TQF (ablation)FADE-TQF on CO-MOT · MOT17HOTA under attack: 39.00 -> 37.26Improved
add L_Decorr to TMC (ablation)FADE-TMC on Samba · MOT17HOTA under attack: 61.63 -> 48.04Improved
add L_Decorr to TMC (ablation)FADE-TMC on CO-MOT · MOT17HOTA under attack: 53.27 -> 41.73Improved
add L_Erase to TMC (ablation)FADE-TMC on Samba · MOT17HOTA under attack: 52.31 -> 48.04Improved
add L_Erase to TMC (ablation)FADE-TMC on CO-MOT and MeMOTR · MOT17HOTA under attack: CO-MOT 41.91 -> 41.73; MeMOTR 41.90 -> 41.56No clear effect
use TQF/TMC instead of association-focused HijackingMOTRv2 · MOT20 (digital)HOTA under attack: 58.27 -> 29.64Improved
use FADE-TMC instead of Daedalus floodingMeMOTR · MOT20 (digital)HOTA under attack: 62.51 -> 37.70Improved
FADE-TQF versus FADE-TMC on MOTRv2 (MOT20)FADE · MOT20 (digital)HOTA under attack: TMC 56.68 vs TQF 29.64Mixed
increase PGD iterations from 5 to 100 for AAI attack (ablation)FADE-TMC AAI on MOTR · MOT17 samplesHOTA under attack: 49.51 -> 39.85Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy