Yoonjun Cho
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1AI×1
Frequent co-authors
Research Timeline
2026
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
The paper introduces a truly benign Direct Preference Optimization (DPO) attack that can jailbreak large language models (LLMs) by fine-tuning them with minimal, harmless preference data, thereby suppressing refusal behavior even for malicious prompts.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIRecentMay 9, 2026
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
Sangyeon Yoon, Wonje Jeung, Yoonjun Cho, Dongjae Jeon +1 more
The paper introduces a truly benign Direct Preference Optimization (DPO) attack that can jailbreak large language models (LLMs) by fine-tuning them with minimal, harmless preference data, thereby supp…
View →