{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:21:23Z","timestamp":1777501283088,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031708893","type":"print"},{"value":"9783031708909","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-70890-9_23","type":"book-chapter","created":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T09:24:24Z","timestamp":1725528264000},"page":"451-470","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["RedactBuster: Entity Type Recognition from\u00a0Redacted Documents"],"prefix":"10.1007","author":[{"given":"Mirco","family":"Beltrame","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mauro","family":"Conti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierpaolo","family":"Guglielmin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesco","family":"Marchiori","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriele","family":"Orazi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,6]]},"reference":[{"key":"23_CR1","unstructured":"Bendersky, M., et al.: Information redaction from document data. US Patent 9,734,148 (2017)"},{"issue":"6","key":"23_CR2","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/MSP.2009.183","volume":"7","author":"E Bier","year":"2009","unstructured":"Bier, E., Chow, R., Goll\u00e9, P., King, T.H., Staddon, J.: The rules of redaction: identify, protect, review (and repeat). IEEE Secur. Priv. 7(6), 46\u201353 (2009)","journal-title":"IEEE Secur. Priv."},{"key":"23_CR3","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.patcog.2018.07.023","volume":"84","author":"B Biggio","year":"2018","unstructured":"Biggio, B., Roli, F.: Wild patterns: ten years after the rise of adversarial machine learning. Pattern Recogn. 84, 317\u2013331 (2018)","journal-title":"Pattern Recogn."},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Bird, S.: NLTK: the natural language toolkit. In: Proceedings of the COLING\/ACL 2006 Interactive Presentation Sessions, pp. 69\u201372 (2006)","DOI":"10.3115\/1225403.1225421"},{"key":"23_CR5","doi-asserted-by":"crossref","unstructured":"Bland, M., Iyer, A., Levchenko, K.: Story beyond the eye: glyph positions break pdf text redaction. In: Proceedings on Privacy Enhancing Technologies (2023)","DOI":"10.56553\/popets-2023-0069"},{"key":"23_CR6","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Mach. Learn. 45, 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"23_CR7","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Chen, T., Guestrin, C.: Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785\u2013794 (2016)","DOI":"10.1145\/2939672.2939785"},{"issue":"2","key":"23_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3440756","volume":"54","author":"X Chen","year":"2021","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: a survey. ACM Comput. Surv. (CSUR) 54(2), 1\u201335 (2021)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"23_CR10","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1162\/tacl_a_00104","volume":"4","author":"JP Chiu","year":"2016","unstructured":"Chiu, J.P., Nichols, E.: Named entity recognition with bidirectional LSTM-CNNs. Trans. Assoc. Comput. Linguist. 4, 357\u2013370 (2016)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"23_CR11","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273\u2013297 (1995)","journal-title":"Mach. Learn."},{"key":"23_CR12","unstructured":"Cottrille, S.C.: Selective document redaction. US Patent 7,913,167 (2011)"},{"key":"23_CR13","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"23_CR14","unstructured":"European Parliament, Council of the European Union: Regulation (EU) 2016\/679 of the European Parliament and of the Council. https:\/\/data.europa.eu\/eli\/reg\/2016\/679\/oj"},{"key":"23_CR15","doi-asserted-by":"publisher","first-page":"863","DOI":"10.1613\/jair.1.11192","volume":"61","author":"A Fern\u00e1ndez","year":"2018","unstructured":"Fern\u00e1ndez, A., Garcia, S., Herrera, F., Chawla, N.V.: Smote for learning from imbalanced data: progress and challenges, marking the 15-year anniversary. J. Artif. Intell. Res. 61, 863\u2013905 (2018)","journal-title":"J. Artif. Intell. Res."},{"key":"23_CR16","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"issue":"6","key":"23_CR17","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1007\/s10618-014-0393-7","volume":"29","author":"S Hajian","year":"2015","unstructured":"Hajian, S., Domingo-Ferrer, J., Monreale, A., Pedreschi, D., Giannotti, F.: Discrimination-and privacy-aware patterns. Data Min. Knowl. Disc. 29(6), 1733\u20131782 (2015)","journal-title":"Data Min. Knowl. Disc."},{"issue":"4","key":"23_CR18","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1515\/popets-2016-0047","volume":"2016","author":"S Hill","year":"2016","unstructured":"Hill, S., Zhou, Z., Saul, L.K., Shacham, H.: On the (in) effectiveness of mosaicing and blurring as tools for document redaction. Proc. Priv. Enhancing Technol. 2016(4), 403\u2013417 (2016)","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"23_CR19","unstructured":"IVASS: I principali numeri delle assicurazioni in italia (2022). https:\/\/www.ivass.it\/pubblicazioni-e-statistiche\/statistiche\/numeri-assicurazioni\/2022\/Focus_I_principali_numeri_2022.pdf. Accessed 17 Apr 2024"},{"issue":"1","key":"23_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","volume":"10","author":"AE Johnson","year":"2023","unstructured":"Johnson, A.E., et al.: Mimic-iv, a freely accessible electronic health record dataset. Sci. Data 10(1), 1 (2023)","journal-title":"Sci. Data"},{"key":"23_CR21","unstructured":"Kelly, D.G., Foster, B.R.: Process for electronic document redaction. US Patent 8,456,654 (2013)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: TrOCR: transformer-based optical character recognition with pre-trained models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, T.: Word embedding for understanding natural language: a survey. In: Guide to Big Data Applications, pp. 83\u2013104 (2018)","DOI":"10.1007\/978-3-319-53817-4_4"},{"key":"23_CR24","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Luoma, J., Pyysalo, S.: Exploring cross-sentence contexts for named entity recognition with BERT. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 904\u2013914 (2020)","DOI":"10.18653\/v1\/2020.coling-main.78"},{"key":"23_CR26","unstructured":"Mane, S.: Method and system for advanced document redaction. US Patent 11,562,134 (2023)"},{"key":"23_CR27","unstructured":"Matichuk, B., Rebstock, J., Kraft, M.: Redaction engine for electronic documents with multiple types, formats and\/or categories. US Patent 10,853,570 (2020)"},{"key":"23_CR28","unstructured":"Microsoft: Presidio: Data protection and de-identification SDK (2022). https:\/\/microsoft.github.io\/presidio\/. Accessed 17 Apr 2024"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Nabbosa, V., Kaar, C.: Societal and ethical issues of digitalization. In: Proceedings of the 2020 International Conference on Big Data in Management, pp. 118\u2013124 (2020)","DOI":"10.1145\/3437075.3437093"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Papadopoulos, C., Pletschacher, S., Clausner, C., Antonacopoulos, A.: The impact dataset of historical document images. In: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing, pp. 123\u2013130 (2013)","DOI":"10.1145\/2501115.2501130"},{"key":"23_CR31","unstructured":"Petro, D.: GitHub - BishopFox\/unredacter: never ever ever use pixelation as a redaction technique \u2014 github.com (2022). https:\/\/github.com\/bishopfox\/unredacter. Accessed 17 Apr 2024"},{"issue":"4","key":"23_CR32","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., Lison, P., \u00d8vrelid, L., Papadopoulou, A., S\u00e1nchez, D., Batet, M.: The text anonymization benchmark (TAB): a dedicated corpus and evaluation framework for text anonymization. Comput. Linguist. 48(4), 1053\u20131101 (2022)","journal-title":"Comput. Linguist."},{"key":"23_CR33","unstructured":"Ramos, I.S., Dickenson, M., Nair, S.: Document redaction and reconciliation. US Patent App. 16\/438,439 (2020)"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Reimers, N., Gurevych, I.: Sentence-BERT: sentence embeddings using siamese BERT-networks. arXiv preprint arXiv:1908.10084 (2019)","DOI":"10.18653\/v1\/D19-1410"},{"key":"23_CR35","unstructured":"Song, C., Shmatikov, V.: Fooling OCR systems with adversarial text images. arXiv preprint arXiv:1802.05385 (2018)"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Tikayat\u00a0Ray, A., Pinon-Fischer, O.J., Mavris, D.N., White, R.T., Cole, B.F.: aeroBERT-NER: named-entity recognition for aerospace requirements engineering using BERT. In: AIAA SCITECH 2023 Forum, p. 2583 (2023)","DOI":"10.2514\/6.2023-2583"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Xu, H., Dong, M., Zhu, D., Kotov, A., Carcone, A.I., Naar-King, S.: Text classification with topic-based word embedding and convolutional neural networks. In: Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pp. 88\u201397 (2016)","DOI":"10.1145\/2975167.2975176"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Xu, X., Chen, J., Xiao, J., Gao, L., Shen, F., Shen, H.T.: What machines see is not what they get: fooling scene text recognition models with adversarial text images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12304\u201312314 (2020)","DOI":"10.1109\/CVPR42600.2020.01232"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, R., Yang, Y., Wang, W.: Research on document digitization processing technology. In: MATEC Web of Conferences, vol.\u00a0309, p. 02014. EDP Sciences (2020)","DOI":"10.1051\/matecconf\/202030902014"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Zhao, X., Greenberg, J., An, Y., Hu, X.T.: Fine-tuning BERT model for materials named entity recognition. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 3717\u20133720. IEEE (2021)","DOI":"10.1109\/BigData52589.2021.9671697"}],"container-title":["Lecture Notes in Computer Science","Computer Security \u2013 ESORICS 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70890-9_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T09:29:29Z","timestamp":1725528569000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70890-9_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031708893","9783031708909"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70890-9_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"6 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ESORICS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Symposium on Research in Computer Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bydgoszcz","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"esorics2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/esorics2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}