Picture for Nanqing Luo

Nanqing Luo

Huazhong University of Science and Technology

Hide Your Malicious Goal Into Benign Narratives: Jailbreak Large Language Models through Neural Carrier Articles

Add code
Aug 20, 2024
Viaarxiv icon

Towards Independence Criterion in Machine Unlearning of Features and Labels

Add code
Mar 12, 2024
Viaarxiv icon

DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing

Add code
Mar 02, 2021
Figure 1 for DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Figure 2 for DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Figure 3 for DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Figure 4 for DPlis: Boosting Utility of Differentially Private Deep Learning via Randomized Smoothing
Viaarxiv icon