@inproceedings{wang-etal-2025-innovative,
    title = "Innovative Image Fraud Detection with Cross-Sample Anomaly Analysis: The Power of {LLM}s",
    author = "Wang, QiWen  and
      Yang, Junqi  and
      Lin, Zhenghao  and
      Ying, Zhenzhe  and
      Wang, Weiqiang  and
      Lin, Chen",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.687/",
    pages = "14058--14078",
    ISBN = "979-8-89176-251-0",
    abstract = "The financial industry faces a substantial workload in verifying document images. Existing methods based on visual features struggle to identify fraudulent document images due to the lack of visual clues on the tampering region. This paper proposes CSIAD (Cross-Sample Image Anomaly Detection) by leveraging LLMs to identify logical inconsistencies in similar images. This novel framework accurately detects forged images with slight tampering traces and explains anomaly detection results. Furthermore, we introduce CrossCred, a new benchmark of real-world fraudulent images with fine-grained manual annotations. Experiments demonstrate that CSIAD outperforms state-of-the-art image fraud detection methods by 79.6{\%} (F1) on CrossCred and deployed industrial solutions by 21.7{\%} (F1) on business data. The benchmark is available at https://github.com/XMUDM/CSIAD."
}