activity
20242026
most citedSecurely Fine-tuning Pre-trained Encoders Against Adversarial Examples

2 citations · 4 across the 7 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.CV2026

Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation

Ziqi Zhou, Yifan Hu, Yufei Song +5

The Segment Anything Model (SAM) achieves remarkable performance in visual segmentation. The latest SAM3 extends promptable segmentation to concept-level prediction, broadening the…