Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (37) · 30943-30950
DOI: 10.1609/aaai.v40i37.40353 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Haorui He und 5 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
State-of-the-art (SOTA) fact-checking systems combat misinformation 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 (explanations for the verdicts). The security of these systems is crucial, as compromised fact-checkers can amplify misinformation, but remains largely underexplored. To bridge this gap, this work introduces a novel threat model against such fact-checking systems and presents Fact2Fiction, the first poisoning attack framework targeting SOTA agentic fact-checking systems. Fact2Fiction employs LLMs to mimic the decomposition strategy and exploit 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 SOTA attacks across various poisoning budgets and exposes security weaknesses in existing fact-checking systems, highlighting the need for defensive countermeasures.
Zitieren
APA
He, H., Li, Y., Zhu, B. B., Wen, D., Cheng, R., & Lau, F. C. M. (2026). Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System. Proceedings of the AAAI Conference on Artificial Intelligence, 40(37), 30943-30950. https://doi.org/10.1609/aaai.v40i37.40353
Vancouver
He H, Li Y, Zhu BB, Wen D, Cheng R, Lau FCM. Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(37):30943-30950. doi:10.1609/aaai.v40i37.40353
BibTeX
@article{He2026,
author = {He, Haorui and Li, Yupeng and Zhu, Bin Benjamin and Wen, Dacheng and Cheng, Reynold and Lau, Francis C. M.},
title = {Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {37},
pages = {30943--30950},
doi = {10.1609/aaai.v40i37.40353}
}
EUVIMED