arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.08050cs.CLcs.LG
收藏

针对大语言模型的对抗性规避攻击效率

Adversarial Evasion Attack Efficiency against Large Language Models

School of Engineering, Polytechnic of Porto (ISEP/IPP)(波尔图理工学院工程学院(ISEP/IPP))

João Vitorino, Eva Maia, Isabel Praça

AI总结:

本文在情感分类任务中评估三类对抗攻击对五个 LLM 的效果,发现词级攻击更有效,而字符级和强约束攻击更省扰动与查询、更具实用性。

摘要:

大语言模型(LLM)在文本分类中具有重要价值,但其脆弱性不容忽视。它们对对抗样本缺乏鲁棒性,因此有必要了解不同类型扰动的影响,并评估普通用户能否借助少量扰动和对已部署 LLM 的少量查询来复现这些攻击。本工作针对情感分类任务,分析了三种不同类型对抗攻击对五个不同 LLM 的有效性、效率和实用性。所得结果表明,词级攻击与字符级攻击具有截然不同的影响。词攻击更有效,但字符攻击以及约束更强的攻击更实用,并且所需的扰动数量和查询次数更少。在制定对抗防御策略以训练面向智能文本分类应用的更鲁棒 LLM 时,需要考虑这些差异。

英文摘要:

Large Language Models (LLMs) are valuable for text classification, but their vulnerabilities must not be disregarded. They lack robustness against adversarial examples, so it is pertinent to understand the impacts of different types of perturbations, and assess if those attacks could be replicated by common users with a small amount of perturbations and a small number of queries to a deployed LLM. This work presents an analysis of the effectiveness, efficiency, and practicality of three different types of adversarial attacks against five different LLMs in a sentiment classification task. The obtained results demonstrated the very distinct impacts of the word-level and character-level attacks. The word attacks were more effective, but the character and more constrained attacks were more practical and required a reduced number of perturbations and queries. These differences need to be considered during the development of adversarial defense strategies to train more robust LLMs for intelligent text classification applications.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑