Author

Li-Feng Lai

h-index 4 View on Semantic Scholar

We have 2 of 18 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Robust Direct Preference Optimization under Preference Label-Flip Attacks

This work establishes deterministic gradient perturbation bounds uniformly over all attack sets containing at most $K$ flips, explicitly separating defense-induced bias from surviving attack effects, and quantifies how quadratic regularization improves curvature while introducing additional bias.

Chen-Ye Yang, Wei-Yu Xu, Li-Feng Lai · 0 citations

2026

Dueling Bandit: Adversarial Attack and Robust Defense

Dueling bandit algorithms excel in learning from pairwise comparisons, offering robust performance guarantees in benign environments. However, recent evidence suggests that even state-of-the-art methods can be highly susceptible to adversarial manipulation. In this work, we introduce and analyze a post-action attack mo...

Mo Lyu, Chen-Ye Yang, Guan-Lin Liu et al. · IEEE Transactions on Signal... · 0 citations