基于大语言模型的对抗说服攻击对事实核查系统的攻击
LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems
AI总结：
本文提出基于大语言模型的说服对抗攻击方法，通过重述声明影响事实核查系统的验证和证据检索效果。
摘要：
自动事实核查（AFC）系统易受对抗攻击，使虚假声明能够逃避检测。现有的对抗框架通常依赖于注入噪声或改变语义，但没有现有框架利用说服技术的对抗潜力，这些技术广泛用于虚假信息运动中以操纵受众。在本文中，我们引入了一种新的说服对抗攻击类别，通过使用生成式大语言模型（LLM）来重述声明，利用说服技术。考虑到15种技术分为6类，我们通过解耦评估策略研究说服对声明验证和证据检索的影响。在FEVER和FEVEROUS基准上的实验表明，说服攻击可以显著降低验证性能和证据检索效果。我们的分析指出说服技术是一种强大的对抗攻击类别，突显了需要更稳健的AFC系统的需求。
英文摘要：
Automated fact-checking (AFC) systems are susceptible to adversarial attacks, enabling false claims to evade detection. Existing adversarial frameworks typically rely on injecting noise or altering semantics, yet no existing framework exploits the adversarial potential of persuasion techniques against AFC systems, which are widely used in disinformation campaigns to manipulate audiences. In this paper, we introduce a novel class of persuasive adversarial attacks on AFCs by employing an LLM to rephrase claims using persuasion techniques. Considering $15$ techniques grouped into $5$ categories, we study the effects of persuasion on both claim verification and evidence retrieval using a decoupled evaluation strategy. Experiments on the FEVER and FEVEROUS benchmarks show that persuasion attacks can substantially degrade both verification performance and evidence retrieval. Our analysis identifies persuasion techniques as a potent class of adversarial attacks, highlighting the need for more robust AFC systems.
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。
