Skip to content

๐Ÿ“„ ai_safety

๐Ÿ’ฌ EMNLP2026 ยท 1 paper notes

LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems

This paper introduces Persuasion Injection Attacks against automated fact-checking (AFC) pipelines, leveraging generative LLMs to inject 15 label-invariant persuasion techniques into claims, and demonstrates through decoupled evaluation that worst-case attacks collapse classification accuracy to near-zero while manipulative wording simultaneously cripples both evidence retrieval and veracity classification.