LLM-Based Adversarial Persuasion Attacks on Fact-Checking Systems

2026-01-23

AI Summary

This work proposes a novel adversarial persuasion attack on automated fact-checking systems, demonstrating that such systems are vulnerable to evasion through strategic manipulation of claims. For the first time, persuasive techniques are integrated into an adversarial attack framework, leveraging large language models to rewrite false claims using 15 distinct strategies across six categories of persuasion. A decoupled evaluation methodology is employed to systematically assess the impact of these attacks on both fact-checking accuracy and evidence retrieval performance. Experiments on the FEVER and FEVEROUS benchmarks reveal that the proposed adversarial persuasion significantly degrades system effectiveness, highlighting the potent capacity of rhetorical strategies to mislead automated fact-checkers. These findings underscore the need to account for persuasive manipulation in the design of more robust fact-checking systems.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Multiagent Systems: Adversarial Agents
• Machine Learning: Adversarial Learning & Robustness

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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 existing framework exploits the adversarial potential of persuasion techniques, 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 a generative LLM to rephrase claims using persuasion techniques. Considering 15 techniques grouped into 6 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.

Problem

• adversarial attacks
• fact-checking systems
• persuasion techniques
• LLM
• disinformation

Innovation

• persuasive adversarial attacks
• large language models
• automated fact-checking
• disinformation
• evidence retrieval