{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:20:38Z","timestamp":1793380838359,"version":"4.5.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:00:00Z","timestamp":1751414400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Symbiosis International"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-04971-9","type":"journal-article","created":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:26:16Z","timestamp":1751415976000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A hybrid rule-based NLP and machine learning approach for PII detection and anonymization in financial documents"],"prefix":"10.1038","volume":"15","author":[{"given":"Kushagra","family":"Mishra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harsh","family":"Pagare","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kanhaiya","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,2]]},"reference":[{"key":"4971_CR1","doi-asserted-by":"publisher","first-page":"114010","DOI":"10.1016\/j.dss.2023.114010","volume":"173","author":"H Liu","year":"2023","unstructured":"Liu, H. et al. Is personally identifiable information really more valuable? Evidence from consumers\u2019 willingness-to-accept valuation of their privacy information. Decis. Support Syst. 173, 114010 (2023).","journal-title":"Decis. Support Syst."},{"key":"4971_CR2","doi-asserted-by":"publisher","first-page":"115939","DOI":"10.1016\/j.chaos.2024.115939","volume":"191","author":"YK Saheed","year":"2025","unstructured":"Saheed, Y. K., Misra, S. & CPS-IoT-PPDNN A new explainable privacy preserving DNN for resilient anomaly detection in Cyber-Physical Systems-enabled IoT networks. Chaos Solitons Fractals. 191, 115939. https:\/\/doi.org\/10.1016\/j.chaos.2024.115939 (2025).","journal-title":"Chaos Solitons Fractals"},{"key":"4971_CR3","doi-asserted-by":"publisher","unstructured":"Yang, J. et al. Exploring the application of large language models in detecting and protecting personally identifiable information in archival data: A comprehensive study*. In. 2023 IEEE International Conference on Big Data (BigData), Sorrento, Italy 2116\u20132123. https:\/\/doi.org\/10.1109\/BigData59044.2023.10386949 (2023).","DOI":"10.1109\/BigData59044.2023.10386949"},{"issue":"6","key":"4971_CR4","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3390\/fi14060167","volume":"14","author":"J Tom\u00e1s","year":"2022","unstructured":"Tom\u00e1s, J., Rasteiro, D. & Bernardino, J. Data anonymization: an experimental evaluation using open-source tools. Future Internet. 14 (6), 167 (2022).","journal-title":"Future Internet"},{"issue":"9","key":"4971_CR5","first-page":"1","volume":"12","author":"P Kulkarni","year":"2021","unstructured":"Kulkarni, P. & Cauvery, N. K. Personally identifiable information (PII) detection in the unstructured large text corpus using natural Language processing and unsupervised learning technique. Int. J. Adv. Comput. Sci. Appl. 12 (9), 1 (2021).","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"4971_CR6","doi-asserted-by":"publisher","unstructured":"Jaikumar, J. & Mohana, S. P. Privacy-Preserving Personal Identifiable Information (PII) Label Detection Using Machine Learning 1\u20135. https:\/\/doi.org\/10.1109\/ICCCNT56998.2023.10307924 (2023).","DOI":"10.1109\/ICCCNT56998.2023.10307924"},{"key":"4971_CR7","unstructured":"Mazzarino, S. et al. NERPII: A python library to perform named entity recognition and generate personal identifiable information. In Proceedings of the Seventh Workshop on Natural Language for Artificial Intelligence (NL4AI 2023) Co-located with 22th International Conference of the Italian Association for Artificial Intelligence (AI* IA 2023)) (2023)."},{"issue":"13","key":"4971_CR8","doi-asserted-by":"publisher","first-page":"5682","DOI":"10.3390\/app14135682","volume":"14","author":"S Jang","year":"2024","unstructured":"Jang, S., Cho, Y., Seong, H., Kim, T. & Woo, H. The development of a named entity recognizer for detecting personal information using a Korean pretrained Language model. Appl. Sci. 14 (13), 5682 (2024).","journal-title":"Appl. Sci."},{"key":"4971_CR9","unstructured":"Mina, M. et al. Extending off-the-shelf NER systems to personal information detection in dialogues with a virtual agent: Findings from a real-life use case. In Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-Pseudo 2024): St. Julian\u2019s, Malta: 21\u201322 March, 2024 44\u201353 (Association for Computational Linguistics, 2024)."},{"key":"4971_CR10","doi-asserted-by":"publisher","unstructured":"Saheed, Y. K. et al. Autoencoder via DCNN and LSTM models for intrusion detection in industrial control systems of critical infrastructures. In 2023 IEEE\/ACM 4th International Workshop on Engineering and Cybersecurity of Critical Systems (EnCyCriS), Melbourne, Australia 9\u201316. https:\/\/doi.org\/10.1109\/EnCyCriS59249.2023.00006 (2023).","DOI":"10.1109\/EnCyCriS59249.2023.00006"},{"key":"4971_CR11","doi-asserted-by":"publisher","unstructured":"Saheed, Y. K. Data Analytics for Intrusion Detection System Based on Recurrent Neural Network and Supervised Machine Learning Methods 167\u2013179. https:\/\/doi.org\/10.1201\/9781003307822-12 (CRC Press, 2022).","DOI":"10.1201\/9781003307822-12"},{"key":"4971_CR12","first-page":"49","volume":"5","author":"AK Makhija","year":"2020","unstructured":"Makhija, A. K. Deep learning application-identifying PII (personally identifiable information) to protect. J. Acc. Finance Econ. Social Sci. 5, 49\u201355 (2020).","journal-title":"J. Acc. Finance Econ. Social Sci."},{"issue":"1","key":"4971_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/6631768","volume":"2021","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Yang, C-Y. & Yang, J. A graph convolutional network-based sensitive information detection algorithm. Complexity 2021 (1), 1\u20138. https:\/\/doi.org\/10.1155\/2021\/6631768 (2021).","journal-title":"Complexity"},{"key":"4971_CR14","doi-asserted-by":"crossref","unstructured":"Yang, L., Tian, M., Xin, D., Cheng, Q. & Zheng, J. AI-Driven Anonymization: Protecting Personal Data Privacy While Leveraging Machine Learning. http:\/\/arXiv.org\/abs\/2402.17191 (2024).","DOI":"10.54254\/2755-2721\/71\/2024MA0053"},{"key":"4971_CR15","doi-asserted-by":"publisher","unstructured":"Hathurusinghe, R. et al. A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning 36\u201345. https:\/\/doi.org\/10.18653\/v1\/2021.privatenlp-1.5 (2021).","DOI":"10.18653\/v1\/2021.privatenlp-1.5"},{"key":"4971_CR16","first-page":"4","volume":"13","author":"B Dash","year":"2022","unstructured":"Dash, B. et al. Federated learning for privacy-preserving: a review of PII data analysis in fintech (July 2022). Int. J. Softw. Eng. Appl. 13, 4 (2022).","journal-title":"Int. J. Softw. Eng. Appl."},{"key":"4971_CR17","first-page":"1","volume":"1","author":"W Ren","year":"2021","unstructured":"Ren, W. et al. Privacy enhancing techniques in the internet of things using data anonymisation. Inf. Syst. Front. 1, 1 (2021).","journal-title":"Inf. Syst. Front."},{"key":"4971_CR18","first-page":"25","volume":"12","author":"A Raj","year":"2021","unstructured":"Raj, A. & D\u2019Souza, R. Anonymization of sensitive data in unstructured documents using NLP. Int. J. Mech. Eng. Technol. 12, 25\u201335 (2021).","journal-title":"Int. J. Mech. Eng. Technol."},{"key":"4971_CR19","first-page":"27","volume":"13","author":"D Garat","year":"2022","unstructured":"Garat, D. & Wonsever, D. Automatic curation of court documents: anonymizing personal data. Inf. 13, 27 (2022).","journal-title":"Inf"},{"issue":"4","key":"4971_CR20","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1162\/coli_a_00458","volume":"48","author":"I Pil\u00e1n","year":"2022","unstructured":"Pil\u00e1n, I. et al. The text anonymization benchmark (TAB): A dedicated corpus and evaluation framework for text anonymization. Comput. Linguistics. 48 (4), 1053\u20131101 (2022).","journal-title":"Comput. Linguistics"},{"key":"4971_CR21","doi-asserted-by":"publisher","first-page":"100297","DOI":"10.1016\/j.sintl.2024.100297","volume":"6","author":"YK Saheed","year":"2025","unstructured":"Saheed, Y. K. et al. A new lightweight threats detection in the industrial IoT via genetic algorithm with attention mechanism and LSTM on multivariate time series sensor data. Sens. Int. 6, 100297. https:\/\/doi.org\/10.1016\/j.sintl.2024.100297 (2025).","journal-title":"Sens. Int."},{"key":"4971_CR22","unstructured":"Kodandaram, S. R. Masking Private User Information Using Natural Language Processing (2021)."},{"issue":"2","key":"4971_CR23","doi-asserted-by":"publisher","first-page":"190","DOI":"10.3390\/jpm12020190","volume":"12","author":"J Lee","year":"2022","unstructured":"Lee, J., Jeong, J., Jung, S., Moon, J. & Rho, S. Verification of de-identification techniques for personal information using tree-based methods with Shapley values. J. Personalized Med. 12 (2), 190 (2022).","journal-title":"J. Personalized Med."},{"key":"4971_CR24","doi-asserted-by":"crossref","unstructured":"Bookert, N. & Anwar, M. Automatic retrieval of privacy factors from IoMT policies: ML and custom NER approach. Usable Security and Privacy (USEC) Symposium (2023).","DOI":"10.14722\/usec.2023.235685"},{"key":"4971_CR25","doi-asserted-by":"publisher","first-page":"103171","DOI":"10.1016\/j.rineng.2024.103171","volume":"24","author":"YK Saheed","year":"2024","unstructured":"Saheed, Y. K. & Chukwuere, J. E. XAIEnsembleTL-IoV: A new eXplainable artificial intelligence ensemble transfer learning for zero-day botnet attack detection in the internet of vehicles. Results Eng. 24, 103171. https:\/\/doi.org\/10.1016\/j.rineng.2024.103171 (2024).","journal-title":"Results Eng."},{"key":"4971_CR26","unstructured":"Dernoncourt, F., Lee, J. Y., Uzuner, O. & Szolovits, P. De-identification of Patient Notes with Recurrent Neural Networks. https:\/\/arxiv.org\/abs\/1606.03475 (2016)."},{"key":"4971_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Y., Lin, F. Y., Ebrahimi, M., Li, W. & Chen, H. Automated PII Extraction from Social Media for Raising Privacy Awareness: A Deep Transfer Learning Approach. https:\/\/arxiv.org\/abs\/2111.09415 (2021).","DOI":"10.1109\/ISI53945.2021.9624678"},{"key":"4971_CR28","unstructured":"Roy, S. & Mitra, M. Identification and Processing of PII Data, Applying Deep Learning Models with Improved Accuracy and Efficiency 34 (2018)."},{"key":"4971_CR29","doi-asserted-by":"publisher","first-page":"10","DOI":"10.30880\/jscdm.2022.03.02.010","volume":"3","author":"N Roslan","year":"2022","unstructured":"Roslan, N. & Foozy, C. A comparison of sensitive information detection framework using LSTM and RNN techniques. J. Soft Comput. Data Min. 3, 10. https:\/\/doi.org\/10.30880\/jscdm.2022.03.02.010 (2022).","journal-title":"J. Soft Comput. Data Min."},{"key":"4971_CR30","unstructured":"Adaptive PII Mitigation Framework for Large Language Models. https:\/\/arxiv.org\/html\/2501.12465v1 (n.d.)."},{"key":"4971_CR31","unstructured":"Benchmarking Advanced Text Anonymization Methods: A Comparative Study on Novel and Traditional Approaches. https:\/\/arxiv.org\/html\/2404.14465v1 (n.d.)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-04971-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-04971-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-04971-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T00:26:21Z","timestamp":1751415981000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-04971-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,2]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["4971"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-04971-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,2]]},"assertion":[{"value":"3 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"22729"}}