22 citations · 34 across the 8 of their papers we have counts for
5 papers · 1 filter
Safety Reasoning with Guidelines
Haoyu Wang, Zeyu Qin, Li Shen +3
Training safe LLMs remains a critical challenge. The most widely used method, Refusal Training (RT), struggles to generalize against various Out-of-Distribution (OOD) jailbreaking…
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
Rui Min, Zeyu Qin, Nevin L. Zhang +2
Backdoor attacks pose a significant threat to Deep Neural Networks (DNNs) as they allow attackers to manipulate model predictions with backdoor triggers. To address these security…
Towards Stable Backdoor Purification through Feature Shift Tuning
Rui Min, Zeyu Qin, Li Shen +1
It has been widely observed that deep neural networks (DNN) are vulnerable to backdoor attacks where attackers could manipulate the model behavior maliciously by tampering with a s…
Revisiting Personalized Federated Learning: Robustness Against Backdoor Attacks
Zeyu Qin, Liuyi Yao, Daoyuan Chen +3
In this work, besides improving prediction accuracy, we study whether personalization could bring robustness benefits to backdoor attacks. We conduct the first study of backdoor at…
Random Noise Defense Against Query-Based Black-Box Attacks
Zeyu Qin, Yanbo Fan, Hongyuan Zha +1
The query-based black-box attacks have raised serious threats to machine learning models in many real applications. In this work, we study a lightweight defense method, dubbed Rand…