Transferable Attacks on Open-Vocabulary Video Instance Segmentation via Dual-Objective Triggers
The Dual-Objective Triggers (DOT) is presented, the first transferable attack on OV-VIS that simultaneously exploits the vision–language coupling and temporal coherence, and Phase-Guided Ad-versarial Training is introduced, which injects perturbations primarily in the phase spectrum while blending amplitudes with clean references.
Minghao Shou, Kesen Wang, Tong Zhang et al.
· 0 citations