Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs

arXiv:2605.10998 · cs.CR, cs.AI · Submitted 2026-05-09 · Read on arXiv

cs.CR, cs.AI

Submitted: 2026-05-09

Updated: 2026-10-14

Terminology

Fine-Tuning — 9× in this paper · explained in 5 episodes
Alignment — 1× in this paper · explained in 1 episode
Direct Preference Optimization — 1× in this paper
Direct Preference Optimization (DPO) — 1× in this paper · explained in 9 episodes
Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes