Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Zhixin, Song, Xurui, Luo, Jun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!