Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
Sangyeon Yoon, Wonje Jeung, Yoonjun Cho +2
Fine-tuning APIs make frontier LLMs easy to customize, but they can also weaken safety alignment during fine-tuning. While prior work shows that benign supervised fine-tuning (SFT)…
cs.CR2024
Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
Sangyeon Yoon, Wonje Jeung, Albert No
Auditing Differentially Private Stochastic Gradient Descent (DP-SGD) in the final model setting is challenging and often results in empirical lower bounds that are significantly lo…