Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

HarryHe11, Yupeng Li, Bin Benjamin Zhu, Dacheng Wen, Reynold Cheng, Francis C. M. Lau

Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System: 4 upvotes on Hugging Face Daily Papers, #25 of 29 papers on 2025-08-12. Day-by-day upvote history.

State-of-the-art fact-checking systems combat misinformation at scale by employing autonomous LLM-based agents to decompose complex claims into smaller sub-claims, verify each sub-claim individually, and aggregate the partial results to produce verdicts with justifications (explanatory rationales for the verdicts). The security of these systems is crucial, as compromised fact-checkers, which tend to be easily underexplored, can amplify misinformation. This work introduces Fact2Fiction, the first poisoning attack framework targeting such agentic fact-checking systems. Fact2Fiction mirrors the decomposition strategy and exploits system-generated justifications to craft tailored malicious evidences that compromise sub-claim verification. Extensive experiments demonstrate that Fact2Fiction achieves 8.9\%--21.2\% higher attack success rates than state-of-the-art attacks across various poisoning budgets. Fact2Fiction exposes security weaknesses in current fact-checking systems and highlights the need for defensive countermeasures.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.