35 citations · 56 across the 21 of their papers we have counts for
5 papers · 1 filter
Does On-Policy Distillation for Safety Pose Backdoor Risks?
Jian Luo, Kehan Qi, Qingqiao Hu +5
On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Recent studies further explore OPD…
Attention-Enhancing Backdoor Attacks Against BERT-based Models
Weimin Lyu, Songzhu Zheng, Lu Pang +2
Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks wi…
Enhancing Clinical Predictive Modeling through Model Complexity-Driven Class Proportion Tuning for Class Imbalanced Data: An Empirical Study on Opioid Overdose Prediction
Yinan Liu, Xinyu Dong, Weimin Lyu +4
Class imbalance problems widely exist in the medical field and heavily deteriorates performance of clinical predictive models. Most techniques to alleviate the problem rebalance cl…
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
Tao Sun, Lu Pang, Weimin Lyu +2
Deep neural networks are vulnerable to backdoor attacks, where an adversary manipulates the model behavior through overlaying images with special triggers. Existing backdoor defens…
Attention Hijacking in Trojan Transformers
Weimin Lyu, Songzhu Zheng, Tengfei Ma +2
Trojan attacks pose a severe threat to AI systems. Recent works on Transformer models received explosive popularity and the self-attentions are now indisputable. This raises a cent…