Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs arXiv:2605.10998v1 Announce Type: new Abstract: 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) can reduce refusal behavior, deployed fine-tuning pipelines increasingly support preference-based objectives, whose safety risks remain less understood. We show that Direct Preference Optimizatio…

https://arxiv.org/abs/2605.10998

sha256:b8a2111d16b80f455ba8123e862fbb2ef8ece2556c1be4ecb014192302d3ed69

• cve0
• md50
• url0
• ipv40
• ipv60
• sha10
• domain0
• sha2560
• malware_token0
• attack_pattern0
• threat_actor_token0