cs.AI updates on arXiv.org 07月30日 12:46
SDD: Self-Degraded Defense against Malicious Fine-tuning
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文揭示了恶意微调LLM的成功原因,并提出了自我退化防御框架,通过使LLM对有害提示产生高质量但无关的响应来提高其安全性。

arXiv:2507.21182v1 Announce Type: cross Abstract: Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tuning succeeds and identify potential defense strategies. Building on the theoretical analysis, we introduce the Self-Degraded Defense (SDD) framework. SDD encourages LLMs to produce high-quality but irrelevant responses to harmful prompts. When attackers attempt malicious fine-tuning, the general capability of the LLM aligned by SDD will significantly decrease, rendering it incapable of following harmful instructions. Our experimental results confirm SDD's effectiveness against such attacks.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

LLM安全 恶意微调 自我退化防御
相关文章