靶向疫苗：通过分层扰动对大型语言模型进行有害微调的安全性校准

IF 8 1区计算机科学 Q1 COMPUTER SCIENCE, THEORY & METHODS

IEEE Transactions on Information Forensics and Security Pub Date : 2025-09-29 DOI:10.1109/tifs.2025.3615412

Guozhi Liu, Weiwei Lin, Qi Mu, Tiansheng Huang, Ruichao Mo, Yuren Tao, Li Shen

引用次数: 0

摘要

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Targeted Vaccine: Safety Alignment for Large Language Models against Harmful Fine-Tuning via Layer-wise Perturbation

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

IEEE Transactions on Information Forensics and Security 工程技术-工程：电子与电气

CiteScore

14.40

自引率

7.40%

发文量

234

审稿时长

6.5 months

期刊介绍： The IEEE Transactions on Information Forensics and Security covers the sciences, technologies, and applications relating to information forensics, information security, biometrics, surveillance and systems applications that incorporate these features