Robust Direct Preference Optimization under Preference Label-Flip Attacks
Direct Preference Optimization (DPO) is widely used for offline Reinforcement Learning from Human Feedback. However, recent works have shown that DPO can be easily manipulated by adversarial preference label flip attacks, which are specifically designed to mislead the learner toward an attacker-chosen target policy. To address this issue, we design robust DPO methods that can defend against such attacks. Building on the property that lable flips induce parameter-independent gradient shifts in log-linear DPO, we propose Trim-$K$ Robust-DPO, which removes the $K$ highest-impact pairs, and Soft-Trim-$K$ Robust-DPO, which smoothly downweights them. We establish deterministic gradient perturba...
| Authors | Chenye Yang, Weiyu Xu, Lifeng Lai |
|---|---|
| Primary category | cs.LG |
| Published | 18 October 2026 |
| Last updated at source | 18 October 2026 |
Popularity, last 4 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.