{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T05:39:41Z","timestamp":1765777181715,"version":"3.48.0"},"reference-count":25,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","funder":[{"name":"the Industry-University Cooperative Education Projects of The Ministry of Education","award":["No. 220605052121135"],"award-info":[{"award-number":["No. 220605052121135"]}]},{"name":"the Fujian Province Science and Technology Innovation Joint Funding","award":["No: 2022R0131"],"award-info":[{"award-number":["No: 2022R0131"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Patt. Recogn. Artif. Intell."],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>Anomaly detection is a fundamental task in modern intelligent systems, yet achieving both robustness and interpretability remains a persistent challenge, especially when labeled data are scarce. Recent advances in contrastive learning have enabled effective representation learning from unlabeled data, but most existing models offer limited insight into the feature-level factors underlying their predictions. In this paper, we propose an interpretable contrastive learning framework for robust and explainable anomaly detection. By integrating a learnable feature attribution mask at the input level directly into the contrastive objective, our approach not only enhances detection accuracy but also provides faithful, sparse attributions for each detected anomaly. Unlike prior interpretable anomaly detection methods, our framework jointly optimizes representation learning and attribution faithfulness, offering both theoretical generalization guarantees and practical scalability for real-world deployment. We conduct comprehensive experiments on four benchmark datasets spanning network intrusion detection, organizational communication analysis, financial fraud identification, and synthetic banking scenarios, and compare our method to both classical and state-of-the-art baselines. The results demonstrate consistent improvements, with our approach achieving up to 4\u20137% higher AUC than recent deep learning baselines, along with high stability of explanations and clear visual separation of anomalies in the learned embedding space. Beyond these quantitative gains, our work underscores the importance of actionable interpretability, providing a principled and deployable solution for anomaly detection in high-stakes domains such as finance, IoT, and cyber-security.<\/jats:p>","DOI":"10.1142\/s0218001425510292","type":"journal-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T09:35:54Z","timestamp":1762940154000},"source":"Crossref","is-referenced-by-count":1,"title":["Interpretable Contrastive Learning for Robust and Explainable Anomaly Detection in Financial and Organizational Data"],"prefix":"10.1142","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8248-7754","authenticated-orcid":false,"given":"Jianti","family":"Zheng","sequence":"first","affiliation":[{"name":"Quanzhou Normal University, Quanzhou, Fujian 362000, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3656-0315","authenticated-orcid":false,"given":"Wenyan","family":"Qiu","sequence":"additional","affiliation":[{"name":"Quanzhou Normal University, Quanzhou, Fujian 362000, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5761-8461","authenticated-orcid":false,"given":"Shiwang","family":"Huang","sequence":"additional","affiliation":[{"name":"The Center for Research & Development, Quanzhou Normal University, Quanzhou, Fujian 362000, P. R. China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"219","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"S0218001425510292BIB001","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.104130"},{"key":"S0218001425510292BIB002","unstructured":"J. V. Alves, D. Leito, S. Jesus, M. O. P. Sampaio, P. Saleiro, M. A. T. Figueiredo and P. Bizarro, FiFAR: A fraud detection dataset for learning to defer, arXiv:2312.13218."},{"key":"S0218001425510292BIB003","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1508821"},{"key":"S0218001425510292BIB004","unstructured":"H. Cho, J. Seol and S.G. Lee, Masked contrastive learning for anomaly detection, arXiv:2105.08793."},{"key":"S0218001425510292BIB005","doi-asserted-by":"publisher","DOI":"10.1109\/DSC54232.2022.9888874"},{"key":"S0218001425510292BIB006","unstructured":"A. Kedia, Financial fraud labeled dataset (2023), https:\/\/huggingface.co\/datasets\/amitkedia\/Financial-Fraud-Dataset."},{"key":"S0218001425510292BIB007","first-page":"92","volume-title":"Int. Conf. Email and Anti-Spam","volume":"45","author":"Klimt B.","year":"2004"},{"key":"S0218001425510292BIB008","doi-asserted-by":"publisher","DOI":"10.1049\/2024\/8821891"},{"key":"S0218001425510292BIB009","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"S0218001425510292BIB010","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102301"},{"key":"S0218001425510292BIB011","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-025-11732-2"},{"key":"S0218001425510292BIB012","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103569"},{"key":"S0218001425510292BIB013","doi-asserted-by":"publisher","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"S0218001425510292BIB014","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00301"},{"key":"S0218001425510292BIB015","first-page":"4393","volume-title":"Int. Conf. Machine Learning","author":"Ruff L.","year":"2018"},{"key":"S0218001425510292BIB016","doi-asserted-by":"publisher","DOI":"10.3390\/app14198884"},{"key":"S0218001425510292BIB017","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965"},{"key":"S0218001425510292BIB018","first-page":"4955","volume-title":"Proc. Thirty-Third Int. Joint Conf. Artificial Intelligence","author":"Tang L.","year":"2024"},{"key":"S0218001425510292BIB019","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2023.1099521"},{"key":"S0218001425510292BIB020","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128379"},{"key":"S0218001425510292BIB021","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3270293"},{"key":"S0218001425510292BIB022","doi-asserted-by":"publisher","DOI":"10.1145\/3691338"},{"key":"S0218001425510292BIB023","unstructured":"J. Zhang, S. Wang and S. Chen, Reconstruction enhanced multi-view contrastive learning for anomaly detection on attributed networks, arXiv:2205.04816."},{"key":"S0218001425510292BIB024","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01660-4"},{"key":"S0218001425510292BIB025","first-page":"1","author":"Pei J.","year":"2025","journal-title":"IEEE Transactions on Intelligent Transportation Systems"}],"container-title":["International Journal of Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0218001425510292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T05:35:22Z","timestamp":1765776922000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/10.1142\/S0218001425510292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":25,"journal-issue":{"issue":"01","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1142\/S0218001425510292"],"URL":"https:\/\/doi.org\/10.1142\/s0218001425510292","relation":{},"ISSN":["0218-0014","1793-6381"],"issn-type":[{"type":"print","value":"0218-0014"},{"type":"electronic","value":"1793-6381"}],"subject":[],"published":{"date-parts":[[2025,11,13]]},"article-number":"2551029"}}