activity
20222025
most citedM-to-N Backdoor Paradigm: A Multi-Trigger and Multi-Target Attack to Deep Learning Models

11 citations · 14 across the 4 of their papers we have counts for

collaborators
Showing 2025Show all

1 paper · 1 filter

cs.CV2025

Test-Time Backdoor Detection for Object Detection Models

Hangtao Zhang, Yichen Wang, Shihui Yan +7

Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. De…