2 citations · 4 across the 4 of their papers we have counts for
Showing cs.CRShow all
2 papers · 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…
cs.CR2024★ 2 cited
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Shaokui Wei, Hongyuan Zha, Baoyuan Wu
Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In…