Author

Han Zhao

1 paper indexed here

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.

#machine learning Jun 2026

RogueMerge: Robust and Unified Attacks against LLM Model Merging

RogueMerge is presented, the first unified attack framework addressing all three challenges of model merging: autoregressive generation, static arithmetic with a joint optimization that explicitly enforces attack success after merging, and attack injection as a stochastic min-max optimization problem and solve it via m...

Jing-Huai Zhang, Ye He, Kun-Lin Cai et al. · arXiv.org · 1 citation