activity
20232026
most citedBreaking the False Sense of Security in Backdoor Defense through Re-Activation Attack

2 citations · 6 across the 9 of their papers we have counts for

collaborators
Showing cs.CRShow all

1 paper · 1 filter

cs.CR2025

Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features

Mingli Zhu, Shaokui Wei, Hongyuan Zha +1

Recent studies have highlighted the vulnerability of deep neural networks to backdoor attacks, where models are manipulated to rely on embedded triggers within poisoned samples, de…