2025
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric.
CoRR, February, 2025

2024
SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance.
CoRR, 2024

CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models.
CoRR, 2024