{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:56:05Z","timestamp":1780707365208,"version":"3.54.1"},"reference-count":42,"publisher":"Association for Computing Machinery (ACM)","issue":"2s","license":[{"start":{"date-parts":[[2022,6,30]],"date-time":"2022-06-30T00:00:00Z","timestamp":1656547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2022,6,30]]},"abstract":"<jats:p>Federated Learning (FL), as an emerging form of distributed machine learning (ML), can protect participants\u2019 private data from being substantially disclosed to cyber adversaries. It has potential uses in many large-scale, data-rich environments, such as the Internet of Things (IoT), Industrial IoT, Social Media (SM), and the emerging SM 3.0. However, federated learning is susceptible to some forms of data leakage through model inversion attacks. Such attacks occur through the analysis of participants\u2019 uploaded model updates. Model inversion attacks can reveal private data and potentially undermine some critical reasons for employing federated learning paradigms. This article proposes novel differential privacy (DP)-based deep federated learning framework. We theoretically prove that our framework can fulfill DP\u2019s requirements under distinct privacy levels by appropriately adjusting scaled variances of Gaussian noise. We then develop a Differentially Private Data-Level Perturbation (DP-DLP) mechanism to conceal any single data point\u2019s impact on the training phase. Experiments on real-world datasets, specifically the social media 3.0, Iris, and Human Activity Recognition (HAR) datasets, demonstrate that the proposed mechanism can offer high privacy, enhanced utility, and elevated efficiency. Consequently, it simplifies the development of various DP-based FL models with different tradeoff preferences on data utility and privacy levels.<\/jats:p>","DOI":"10.1145\/3537899","type":"journal-article","created":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T08:54:13Z","timestamp":1653296053000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Perturbation-enabled Deep Federated Learning for Preserving Internet of Things-based Social Networks"],"prefix":"10.1145","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0577-4625","authenticated-orcid":false,"given":"Sara","family":"Salim","sequence":"first","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales at ADFA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6127-9349","authenticated-orcid":false,"given":"Nour","family":"Moustafa","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales at ADFA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0440-5032","authenticated-orcid":false,"given":"Benjamin","family":"Turnbull","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales at ADFA, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3930-6600","authenticated-orcid":false,"given":"Imran","family":"Razzak","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, University of New South Wales, Sydney, New South Wales, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,6]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2942190"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3426474"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3088410"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2021.102402"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3293578.3293589"},{"key":"e_1_3_1_7_2","unstructured":"Retrieved September 14 2021 from https:\/\/www.upguard.com\/blog\/australian-data-breach-stats 2021 13 Critical Data Breach Stats for Australian Businesses in 2021 | UpGuard"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom50675.2020.00115"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3165265"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3524135"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70604-3_3"},{"key":"e_1_3_1_12_2","unstructured":"Tom Titcombe Adam J. Hall Pavlos Papadopoulos and Daniele Romanini. 2021. Practical defences against model inversion attacks for split neural networks. arXiv:2104.05743. Retrieved from https:\/\/arxiv.org\/abs\/2104.05743."},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"e_1_3_1_14_2","unstructured":"Jonas Geiping Hartmut Bauermeister Hannah Dr\u00f6ge and Michael Moeller. 2020. Inverting gradients\u2013how easy is it to break privacy in federated learning? In Advances in Neural Information Processing Systems Vol. 33. Curran Associates Inc. 16937\u201316947. https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/c4ede56bbd98819ae6112b20ac6bf145-Paper.pdf."},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2021.102685"},{"issue":"1","key":"e_1_3_1_16_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3279952","article-title":"Deep learning\u2013based multimedia analytics: A review","volume":"15","author":"Zhang Wei","year":"2019","unstructured":"Wei Zhang, Ting Yao, Shiai Zhu, and Abdulmotaleb El Saddik. 2019. Deep learning\u2013based multimedia analytics: A review. ACM Transactions on Multimedia Computing, Communications, and Applications 15, 1s (2019), 1\u201326.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"e_1_3_1_17_2","unstructured":"Yilin Kang Yong Liu Ben Niu Xinyi Tong Likun Zhang and Weiping Wang. 2020. Input perturbation: A new paradigm between central and local differential privacy. arXiv:2002.08570. Retrieved from https:\/\/arxiv.org\/abs\/2002.08570."},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2991401"},{"key":"e_1_3_1_19_2","first-page":"1","article-title":"Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT","author":"Jia Bin","year":"2021","unstructured":"Bin Jia, Xiaosong Zhang, Jiewen Liu, Yang Zhang, Ke Huang, and Yongquan Liang. 2021. Blockchain-enabled federated learning data protection aggregation scheme with differential privacy and homomorphic encryption in IIoT. IEEE Transactions on Industrial Informatics 18, 6 (2021), 1\u20131.","journal-title":"IEEE Transactions on Industrial Informatics"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.29012\/jpc.v7i3.405"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2021.3134463"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486242"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3217804.3217907"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2810062"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2974555"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2978771"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2978568"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-6604-2"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2924045"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.0211.2100002"},{"key":"e_1_3_1_31_2","article-title":"De-identification of personal information","author":"Garfinkel Simson L.","year":"2015","unstructured":"Simson L. Garfinkel. 2015. De-identification of personal information. National Institute of Standards and Technology (2015), 1\u201346.","journal-title":"National Institute of Standards and Technology"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2840974"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxz069"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2706947"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3045700"},{"key":"e_1_3_1_36_2","unstructured":"Robin C. Geyer Tassilo Klein and Moin Nabi. 2017. Differentially private federated learning: A client level perspective. arXiv:1712.07557. Retrieved from https:\/\/arxiv.org\/abs\/1712.07557."},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.07.009"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3338501.3357370"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2022.102786"},{"key":"e_1_3_1_40_2","unstructured":"Dheeru Dua and Casey Graff. 2017. UCI Machine Learning Repository. Retrieved Accessed 27 January 2022 from http:\/\/archive.ics.uci.edu\/ml."},{"key":"e_1_3_1_41_2","article-title":"A Public Domain Dataset for Human Activity Recognition Using Smartphones","author":"Ghio Luca Oneto Xavier Parra Davide Anguita, Alessandro","year":"2013","unstructured":"Luca Oneto Xavier Parra Davide Anguita, Alessandro Ghio and Jorge L. 2013. A Public Domain Dataset for Human Activity Recognition Using Smartphones. Retrieved January 27, 2022 from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Human+Activity+Recognition+Using+Smartphones.","journal-title":"Retrieved January 27, 2022 from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Human+Activity+Recognition+Using+Smartphones"},{"key":"e_1_3_1_42_2","first-page":"370","volume-title":"Proceedings of the International Conference on Information Security and Cryptology","author":"Zhu Xudong","year":"2018","unstructured":"Xudong Zhu, Hui Li, and Yang Yu. 2018. Blockchain-based privacy preserving deep learning. In Proceedings of the International Conference on Information Security and Cryptology. Springer, 370\u2013383."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-019-01445-x"}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3537899","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3537899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:13Z","timestamp":1750186813000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3537899"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,30]]},"references-count":42,"journal-issue":{"issue":"2s","published-print":{"date-parts":[[2022,6,30]]}},"alternative-id":["10.1145\/3537899"],"URL":"https:\/\/doi.org\/10.1145\/3537899","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,30]]},"assertion":[{"value":"2021-11-28","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-06","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-06","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}