pith. sign in

Merger-as-a-stealer: Stealing targeted pii from aligned llms with model merging,

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CR 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

RogueMerge: Robust and Unified Attacks against LLM Model Merging

cs.CR · 2026-06-02 · unverdicted · novelty 7.0

RogueMerge is a unified attack method that jointly optimizes task vectors to succeed after merging, using stochastic min-max simulation for unknown merging settings and a Taylor-approximated DRO for prompt generalization on generative LLMs.

citing papers explorer

Showing 1 of 1 citing paper.

  • RogueMerge: Robust and Unified Attacks against LLM Model Merging cs.CR · 2026-06-02 · unverdicted · none · ref 54

    RogueMerge is a unified attack method that jointly optimizes task vectors to succeed after merging, using stochastic min-max simulation for unknown merging settings and a Taylor-approximated DRO for prompt generalization on generative LLMs.