{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T21:40:07Z","timestamp":1748641207460,"version":"3.41.0"},"reference-count":16,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,2,25]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Machine learning (ML) is increasingly deployed in critical domains such as healthcare, finance, and autonomous driving, where the use of sensitive data raises significant privacy challenges. My research places individuals and their data at the center of ML privacy, building systems that protect individuals\u2019 privacy without sacrificing performance. I focus on (1) exploring the threat space in ML privacy to inspire targeted protection, (2) analyzing the root cause of privacy leakage from ML models, and (3) developing individualized privacy guarantees that protect data according to individuals\u2019 unique needs while improving privacy-utility trade-offs. My vision is to advance privacy-preserving ML to address the evolving challenges of increasingly complex ML models and systems. As models grow in scale, integrate diverse data modalities, and become embedded in critical societal applications, protecting individual privacy becomes both more urgent but also more challenging. My goal is to create methods that ensure privacy across a broad spectrum of ML applications, while also addressing the interplay between privacy and other trustworthy ML aspects, and aligning technical privacy measures with legal and societal expectations to meet individual rights.<\/jats:p>","DOI":"10.1515\/itit-2024-0101","type":"journal-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T10:56:15Z","timestamp":1743504975000},"page":"8-12","source":"Crossref","is-referenced-by-count":0,"title":["A self-portrayal of GI Junior Fellow Franziska Boenisch: trustworthy machine learning for individuals"],"prefix":"10.1515","volume":"67","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2111-2234","authenticated-orcid":false,"given":"Franziska","family":"Boenisch","sequence":"first","affiliation":[{"name":"CISPA , Saarbr\u00fccken , Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"374","published-online":{"date-parts":[[2025,4,2]]},"reference":[{"key":"2025053021205069839_j_itit-2024-0101_ref_001","doi-asserted-by":"crossref","unstructured":"F. Boenisch, V. Battis, N. Buchmann, and M. Poikela, \u201c\u201cI never thought about securing my machine learning systems\u201d: a study of security and privacy awareness of machine learning practitioners,\u201d in Mensch und Computer 2021, 2021, pp.\u00a0520\u2013546.","DOI":"10.1145\/3473856.3473869"},{"key":"2025053021205069839_j_itit-2024-0101_ref_002","doi-asserted-by":"crossref","unstructured":"F. Boenisch, A. Dziedzic, R. Schuster, A. S. Shamsabadi, I. Shumailov, and N. Papernot, \u201cWhen the curious abandon honesty: federated learning is not private,\u201d in 8th IEEE European Symposium on Security and Privacy (EuroS&P \u201923), 2023.","DOI":"10.1109\/EuroSP57164.2023.00020"},{"key":"2025053021205069839_j_itit-2024-0101_ref_003","doi-asserted-by":"crossref","unstructured":"F. Boenisch, A. Dziedzic, R. Schuster, A. S. Shamsabadi, I. Shumailov, and N. Papernot, \u201cReconstructing individual data points in federated learning hardened with differential privacy and secure aggregation,\u201d in 8th IEEE European Symposium on Security and Privacy (EuroS&P \u201923), 2023.","DOI":"10.1109\/EuroSP57164.2023.00023"},{"key":"2025053021205069839_j_itit-2024-0101_ref_004","unstructured":"N. Franzese, et al.., \u201cRobust and actively secure serverless collaborative learning,\u201d Adv. Neural Inf. Process. Syst., vol.\u00a036, 2024."},{"key":"2025053021205069839_j_itit-2024-0101_ref_005","unstructured":"W. Wang, M. Ahmad Kaleem, A. Dziedzic, M. Backes, N. Papernot, and F. Boenisch, \u201cMemorization in self-supervised learning improves downstream generalization,\u201d in The Twelfth International Conference on Learning Representations (ICLR), 2023."},{"key":"2025053021205069839_j_itit-2024-0101_ref_006","unstructured":"W. Wang, A. Dziedzic, M. Backes, and F. Boenisch, \u201cLocalizing memorization in ssl vision encoders,\u201d in Accepted for: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a038, 2024."},{"key":"2025053021205069839_j_itit-2024-0101_ref_007","unstructured":"D. Hintersdorf, L. Struppek, K. Kersting, A. Dziedzic, and F. Boenisch, \u201cFinding nemo: localizing neurons responsible for memorization in diffusion models,\u201d in Accepted for: Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a038, 2024."},{"key":"2025053021205069839_j_itit-2024-0101_ref_008","doi-asserted-by":"crossref","unstructured":"F. Boenisch, C. M\u00fchl, R. Rinberg, J. Ihrig, and A. Dziedzic, \u201cIndividualized pate: differentially private machine learning with individual privacy guarantees,\u201d in 23rd Privacy Enhancing Technologies Symposium (PoPETs), 2023.","DOI":"10.56553\/popets-2023-0010"},{"key":"2025053021205069839_j_itit-2024-0101_ref_009","unstructured":"N. Papernot, M. Abadi, \u00da. Erlingsson, I. Goodfellow, and K. Talwar, \u201cSemi-supervised knowledge transfer for deep learning from private training data,\u201d in International Conference on Learning Representations, 2016."},{"key":"2025053021205069839_j_itit-2024-0101_ref_010","doi-asserted-by":"crossref","unstructured":"F. Boenisch, C. M\u00fchl, A. Dziedzic, R. Rinberg, and N. Papernot, \u201cHave it your way: individualized privacy assignment for dp-sgd,\u201d in Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a037, 2023.","DOI":"10.56553\/popets-2023-0010"},{"key":"2025053021205069839_j_itit-2024-0101_ref_011","doi-asserted-by":"crossref","unstructured":"M. Abadi, et al.., \u201cDeep learning with differential privacy,\u201d in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp.\u00a0308\u2013318.","DOI":"10.1145\/2976749.2978318"},{"key":"2025053021205069839_j_itit-2024-0101_ref_012","unstructured":"A. Kowalczuk, et al.., \u201cBenchmarking robust self-supervised learning across diverse downstream tasks,\u201d in ICML 2024 Workshop on Foundation Models in the Wild, 2024."},{"key":"2025053021205069839_j_itit-2024-0101_ref_013","unstructured":"J. Wu, A. A. Ghomi, D. Glukhov, J. C. Cresswell, F. Boenisch, and N. Papernot, \u201cAugment then smooth: reconciling differential privacy with certified robustness,\u201d Trans. Mach. Learn. (TMLR), 2024. https:\/\/openreview.net\/forum?id=YN0IcnXqsr."},{"key":"2025053021205069839_j_itit-2024-0101_ref_014","unstructured":"M. Yaghini, P. Liu, F. Boenisch, and N. Papernot, \u201cLearning to walk impartially on the pareto frontier of fairness, privacy, and utility,\u201d in NeurIPS 2023 Workshop on Regulatable ML, 2023."},{"key":"2025053021205069839_j_itit-2024-0101_ref_015","unstructured":"M. Yaghini, P. Liu, F. Boenisch, and N. Papernot, \u201cRegulation games for trustworthy machine learning,\u201d in NeurIPS 2023 Workshop on Regulatable ML, 2023."},{"key":"2025053021205069839_j_itit-2024-0101_ref_016","doi-asserted-by":"crossref","unstructured":"M. Giomi, F. Boenisch, C. Wehmeyer, and B. Tasn\u00e1di, \u201cA unified framework for quantifying privacy risk in synthetic data,\u201d in 23rd Privacy Enhancing Technologies Symposium (PoPETs), 2023.","DOI":"10.56553\/popets-2023-0055"}],"container-title":["it - Information Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/itit-2024-0101\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/itit-2024-0101\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T21:21:30Z","timestamp":1748640090000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/itit-2024-0101\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,1]]},"references-count":16,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,4,24]]},"published-print":{"date-parts":[[2025,2,25]]}},"alternative-id":["10.1515\/itit-2024-0101"],"URL":"https:\/\/doi.org\/10.1515\/itit-2024-0101","relation":{},"ISSN":["1611-2776","2196-7032"],"issn-type":[{"type":"print","value":"1611-2776"},{"type":"electronic","value":"2196-7032"}],"subject":[],"published":{"date-parts":[[2025,2,1]]}}}