English(EN) LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems

LLM被用于制造欺骗事实核查系统的说服性攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-25 04:00

研究人员开发了一种攻击自动化事实核查（AFC）系统的新方法，该方法利用大型语言模型（LLM）使用说服性语言重述主张。这种方法将15种说服技巧分类，并在FEVER和FEVEROUS基准上进行了测试。实验表明，这些说服性攻击显著损害了主张验证的准确性和支持性证据的检索，表明当前AFC系统存在漏洞。 AI

影响凸显了AI事实核查系统的新漏洞，需要更强大的防御措施来应对LLM驱动的虚假信息。

排序理由该集群包含一篇详细介绍新研究发现的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍新研究发现的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 1 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Jo\~ao A. Leite, Olesya Razuvayevskaya, Kalina Bontcheva, Carolina Scarton · 2026-08-25 04:00

基于大语言模型的对抗性说服攻击事实核查系统

arXiv:2601.16890v2 Announce Type: replace-cross Abstract: 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 existi…

本文如何被排名

报道来源 [1]

基于大语言模型的对抗性说服攻击事实核查系统

相关实体

相关话题