{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T12:08:46Z","timestamp":1779365326860,"version":"3.53.0"},"reference-count":113,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Networks"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.comnet.2026.112335","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T15:52:21Z","timestamp":1776959541000},"page":"112335","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Differential privacy for data sharing: evolution and full-lifecycle applications in generative AI"],"prefix":"10.1016","volume":"284","author":[{"given":"Boyan","family":"Gao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lichuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aimin","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.comnet.2026.112335_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3298981","article-title":"Federated machine learning: concept and applications","volume":"10","author":"Yang","year":"2019","journal-title":"ACM TIST"},{"key":"10.1016\/j.comnet.2026.112335_bib0002","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1109\/OJCOMS.2025.3644477","article-title":"A survey on security and privacy in federated learning-based intrusion detection systems for 5G and beyond networks","volume":"7","author":"Rezaei","year":"2025","journal-title":"IEEE Open J. Commun. Soci."},{"key":"10.1016\/j.comnet.2026.112335_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2024.111023","article-title":"A review of federated learning applications in intrusion detection systems","volume":"258","author":"Belenguer","year":"2025","journal-title":"Comput. Netw."},{"issue":"5","key":"10.1016\/j.comnet.2026.112335_bib0004","doi-asserted-by":"crossref","first-page":"4745","DOI":"10.1007\/s43681-025-00797-3","article-title":"Deconstructing the ethics of large language models from long-standing issues to new-emerging dilemmas: a survey","volume":"5","author":"Deng","year":"2025","journal-title":"AI. Ethics"},{"issue":"05","key":"10.1016\/j.comnet.2026.112335_bib0005","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1142\/S0218488502001648","article-title":"k-anonymity: a model for protecting privacy","volume":"10","author":"Sweeney","year":"2002","journal-title":"Int. J. Uncertainty Fuzziness Knowl. Based Syst.,"},{"key":"10.1016\/j.comnet.2026.112335_bib0006","series-title":"2008 IEEE Symposium on Security and Privacy (SP 2008)","first-page":"111","article-title":"Robust de-anonymization of large sparse datasets [C]","author":"Narayanan","year":"2008"},{"key":"10.1016\/j.comnet.2026.112335_bib0007","series-title":"Theory of Cryptography Conference","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis [C]","author":"Dwork","year":"2006"},{"issue":"8","key":"10.1016\/j.comnet.2026.112335_bib0008","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.1109\/TKDE.2017.2697856","article-title":"Differentially private data publishing and analysis: a survey","volume":"29","author":"Zhu","year":"2017","journal-title":"IEEe Trans. Knowl. Data Eng."},{"issue":"1","key":"10.1016\/j.comnet.2026.112335_bib0009","doi-asserted-by":"crossref","first-page":"746","DOI":"10.1109\/COMST.2019.2944748","article-title":"Differential privacy techniques for cyber physical systems: a survey","volume":"22","author":"Hassan","year":"2019","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"10.1016\/j.comnet.2026.112335_bib0010","doi-asserted-by":"crossref","DOI":"10.1109\/TR.2025.3587088","article-title":"Da-FL: blockchain-empowered secure and private federated learning with anonymous authentication","author":"Xiong","year":"2025","journal-title":"IEEe Trans. Reliab."},{"key":"10.1016\/j.comnet.2026.112335_bib0011","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-025-02280-z","article-title":"Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications","author":"Mohammadi","year":"2026","journal-title":"NPJ. Digit. Med."},{"key":"10.1016\/j.comnet.2026.112335_bib0012","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2025.3565175","article-title":"Zeal-differential privacy mechanism for IoT enhancing compression efficiency","author":"Taurone","year":"2025","journal-title":"IEEe Internet. Things. J."},{"key":"10.1016\/j.comnet.2026.112335_bib0013","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2025.3594082","article-title":"Enhancing privacy-preservation of IoT-based smart City using software defined networking and differential privacy distributions","author":"Gheisari","year":"2025","journal-title":"IEEe Internet. Things. J."},{"key":"10.1016\/j.comnet.2026.112335_bib0014","series-title":"Annual International Conference on the Theory and Applications of Cryptographic Techniques","first-page":"486","article-title":"Our data, ourselves: privacy via distributed noise generation [C]","author":"Dwork","year":"2006"},{"key":"10.1016\/j.comnet.2026.112335_bib0015","series-title":"2026 SIAM Symposium on Simplicity in Algorithms (SOSA)","first-page":"192","article-title":"Efficient derandomization of differentially private counting queries [C]","author":"Ghentiyala","year":"2026"},{"key":"10.1016\/j.comnet.2026.112335_bib0016","article-title":"Balancing differential privacy and utility: a relevance-based adaptive private fine-tuning framework for language models","author":"Wang","year":"2024","journal-title":"IEEE Trans. Info. Forensics Secur."},{"key":"10.1016\/j.comnet.2026.112335_bib0017","series-title":"International Conference on Learning Representations (ICLR)","first-page":"1376","article-title":"The composition theorem for differential privacy [C]","author":"Kairouz","year":"2015"},{"issue":"8","key":"10.1016\/j.comnet.2026.112335_bib0018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3651153","article-title":"Scenario-based adaptations of differential privacy: a technical survey","volume":"56","author":"Zhao","year":"2024","journal-title":"ACM. Comput. Surv."},{"key":"10.1016\/j.comnet.2026.112335_bib0019","series-title":"48th Annual IEEE Symposium on Foundations of Computer Science (FOCS'07)","first-page":"94","article-title":"Mechanism design via differential privacy [C]","author":"McSherry","year":"2007"},{"issue":"6","key":"10.1016\/j.comnet.2026.112335_bib0020","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1007\/s00778-015-0398-x","article-title":"The matrix mechanism: optimizing linear counting queries under differential privacy","volume":"24","author":"Li","year":"2015","journal-title":"VLDB J."},{"key":"10.1016\/j.comnet.2026.112335_bib0021","series-title":"International Conference on Machine Learning","first-page":"2436","article-title":"Discrete distribution estimation under local privacy [C]","author":"Kairouz","year":"2016"},{"key":"10.1016\/j.comnet.2026.112335_bib0022","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1109\/TIFS.2025.3639964","article-title":"VPrivKV: verifiable local differential privacy for key-value data","volume":"21","author":"Zhou","year":"2025","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.1016\/j.comnet.2026.112335_bib0023","article-title":"Cokv: key-value data collection with condensed local differential privacy","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Info. Forensics Secur."},{"key":"10.1016\/j.comnet.2026.112335_bib0024","series-title":"Annual International Conference on the Theory and Applications of Cryptographic Techniques","first-page":"375","article-title":"Distributed differential privacy via shuffling [C]","author":"Cheu","year":"2019"},{"key":"10.1016\/j.comnet.2026.112335_bib0025","author":"Melis"},{"key":"10.1016\/j.comnet.2026.112335_bib0026","author":"Yousefpour"},{"key":"10.1016\/j.comnet.2026.112335_bib0027","series-title":"Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security","first-page":"308","article-title":"Deep learning with differential privacy [C]","author":"Abadi","year":"2016"},{"key":"10.1016\/j.comnet.2026.112335_bib0028","unstructured":"Gaboardi M, Hay M, Vadhan S. A programming framework for opendp. Manuscript, 2020."},{"key":"10.1016\/j.comnet.2026.112335_bib0029","author":"Murakonda"},{"key":"10.1016\/j.comnet.2026.112335_bib0030","series-title":"Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021","first-page":"3853","article-title":"Differential privacy for text analytics via natural text sanitization [C]","author":"Yue","year":"2021"},{"key":"10.1016\/j.comnet.2026.112335_bib0031","series-title":"Theory of Cryptography Conference","first-page":"635","article-title":"Concentrated differential privacy: simplifications, extensions, and lower bounds [C]","author":"Bun","year":"2016"},{"key":"10.1016\/j.comnet.2026.112335_bib0032","series-title":"2017 IEEE 30th Computer Security Foundations Symposium (CSF)","first-page":"263","article-title":"R\u00e9nyi differential privacy [C]","author":"Mironov","year":"2017"},{"issue":"1","key":"10.1016\/j.comnet.2026.112335_bib0033","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1111\/rssb.12454","article-title":"Gaussian differential privacy","volume":"84","author":"Dong","year":"2022","journal-title":"J. R. Stat. Soc. Ser. B Stat. Methodol."},{"key":"10.1016\/j.comnet.2026.112335_bib0034","series-title":"International Conference on Artificial Intelligence and Statistics","first-page":"2560","article-title":"Computing tight differential privacy guarantees using FFT [C]","author":"Koskela","year":"2020"},{"issue":"4","key":"10.1016\/j.comnet.2026.112335_bib0035","doi-asserted-by":"crossref","first-page":"552","DOI":"10.56553\/popets-2022-0122","article-title":"Connect the dots: tighter discrete approximations of privacy loss distributions","volume":"2022","author":"Doroshenko","year":"2022","journal-title":"Proc. Privacy Enhancing Technol."},{"key":"10.1016\/j.comnet.2026.112335_bib0036","series-title":"Proceedings of the 13th International Conference on Web Search and Data Mining","first-page":"178","article-title":"Privacy-and utility-preserving textual analysis via calibrated multivariate perturbations [C]","author":"Feyisetan","year":"2020"},{"key":"10.1016\/j.comnet.2026.112335_bib0037","article-title":"Dynamic gradient noise adaptation with reinforcement learning for differential privacy deep learning","author":"Li","year":"2025","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.comnet.2026.112335_bib0038","article-title":"Personalized local differential privacy for multi-dimensional range queries over mobile user data","author":"He","year":"2025","journal-title":"IEEe Trans. Mob. Comput."},{"key":"10.1016\/j.comnet.2026.112335_bib0039","series-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","first-page":"1656","article-title":"Concentrated differentially private gradient descent with adaptive per-iteration privacy budget [C]","author":"Lee","year":"2018"},{"key":"10.1016\/j.comnet.2026.112335_bib0040","series-title":"Proceedings of the Sixth ACM Conference on Data and Application Security and Privacy","first-page":"26","article-title":"Differentially private k-means clustering [C]","author":"Su","year":"2016"},{"key":"10.1016\/j.comnet.2026.112335_bib0041","series-title":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","first-page":"289","article-title":"Private spatial data aggregation in the local setting [C]","author":"Chen","year":"2016"},{"issue":"11","key":"10.1016\/j.comnet.2026.112335_bib0042","doi-asserted-by":"crossref","first-page":"2599","DOI":"10.14778\/3551793.3551817","article-title":"AIM: an adaptive and iterative mechanism for differentially private synthetic data","volume":"15","author":"McKenna","year":"2022","journal-title":"Proc. VLDB Endowment"},{"key":"10.1016\/j.comnet.2026.112335_bib0043","series-title":"International Conference on Learning Representations (ICLR)","article-title":"PATE-GAN: generating synthetic data with differential privacy guarantees [C]","author":"Jordon","year":"2018"},{"key":"10.1016\/j.comnet.2026.112335_bib0044","article-title":"Differentially private diffusion models","author":"Dockhorn","year":"2023","journal-title":"Trans. Machine Learn. Res."},{"key":"10.1016\/j.comnet.2026.112335_bib0045","series-title":"Proceedings of the 2022 IEEE Symposium on Security and Privacy (SP)","first-page":"1889","article-title":"Benchmarking differentially private synthetic data generation algorithms [C]","author":"Tao","year":"2022"},{"key":"10.1016\/j.comnet.2026.112335_bib0046","doi-asserted-by":"crossref","DOI":"10.1109\/TKDE.2025.3603731","article-title":"Differential privacy configurations in the real world: a comparative analysis","author":"Khavkin","year":"2025","journal-title":"IEEe Trans. Knowl. Data Eng."},{"key":"10.1016\/j.comnet.2026.112335_bib0047","article-title":"Robust and secure federated learning with verifiable differential privacy","author":"Zhang","year":"2025","journal-title":"IEEe Trans. Dependable Secure Comput."},{"key":"10.1016\/j.comnet.2026.112335_bib0048","article-title":"Exploring the vulnerabilities of federated learning: a deep dive into gradient inversion attacks","author":"Guo","year":"2025","journal-title":"IEEe Trans. Pattern. Anal. Mach. Intell."},{"key":"10.1016\/j.comnet.2026.112335_bib0049","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2025.3595533","article-title":"PPFL: privacy-preserving federated learning based on differential privacy and personalized data transformation","author":"Han","year":"2025","journal-title":"IEEe Internet. Things. J."},{"issue":"11","key":"10.1016\/j.comnet.2026.112335_bib0050","doi-asserted-by":"crossref","DOI":"10.2196\/26914","article-title":"Local differential privacy in the medical domain to protect sensitive information: algorithm development and real-world validation","volume":"9","author":"Sung","year":"2021","journal-title":"JMIR. Med. Inform."},{"issue":"1","key":"10.1016\/j.comnet.2026.112335_bib0051","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1038\/s41746-020-00323-1","article-title":"The future of digital health with federated learning","volume":"3","author":"Rieke","year":"2020","journal-title":"NPJ. Digit. Med."},{"issue":"1","key":"10.1016\/j.comnet.2026.112335_bib0052","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/TNSE.2023.3304413","article-title":"Local differential privacy-based privacy-preserving data range query scheme for electric vehicle charging","volume":"11","author":"Ju","year":"2023","journal-title":"IEEe Trans. Netw. Sci. Eng."},{"issue":"2","key":"10.1016\/j.comnet.2026.112335_bib0053","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1109\/TSG.2023.3315690","article-title":"Privacy preserving user energy consumption profiling: from theory to application","volume":"15","author":"Lu","year":"2023","journal-title":"IEEe Trans. Smart. Grid."},{"key":"10.1016\/j.comnet.2026.112335_bib0054","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2025.3594082","article-title":"Enhancing privacy-preservation of IoT-based smart City using software defined networking and differential privacy distributions","author":"Gheisari","year":"2025","journal-title":"IEEe Internet. Things. J."},{"key":"10.1016\/j.comnet.2026.112335_bib0055","article-title":"Approx-PSI: efficient differentially private set intersection-based analysis","author":"Long","year":"2025","journal-title":"IEEe Trans. Dependable Secure Comput."},{"key":"10.1016\/j.comnet.2026.112335_bib0056","doi-asserted-by":"crossref","first-page":"11150","DOI":"10.1109\/TIFS.2025.3620213","article-title":"Differentially private vertical federated learning with adaptive constraints and dynamic noise","volume":"20","author":"Gai","year":"2025","journal-title":"IEEE Trans. Info. Forensics Secur."},{"key":"10.1016\/j.comnet.2026.112335_bib0057","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4642","article-title":"He B. Practical federated gradient boosting decision trees [C]","volume":"34","author":"Li","year":"2020"},{"key":"10.1016\/j.comnet.2026.112335_bib0058","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Semi-supervised knowledge transfer for deep learning from private training data [C]","author":"Papernot","year":"2017"},{"issue":"4","key":"10.1016\/j.comnet.2026.112335_bib0059","doi-asserted-by":"crossref","first-page":"4298","DOI":"10.1109\/TVT.2020.2973651","article-title":"Blockchain-empowered asynchronous federated learning for secure data sharing in the internet of vehicles","volume":"69","author":"Lu","year":"2020","journal-title":"IEEe Trans. Veh. Technol."},{"key":"10.1016\/j.comnet.2026.112335_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2024.111023","article-title":"A review of federated learning applications in intrusion detection systems","volume":"258","author":"Belenguer","year":"2025","journal-title":"Comput. Netw."},{"key":"10.1016\/j.comnet.2026.112335_bib0061","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comnet.2026.112335_bib0062","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans. Info. Forensics Secur."},{"key":"10.1016\/j.comnet.2026.112335_bib0063","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2024.110822","article-title":"Local differential privacy federated learning based on heterogeneous data multi-privacy mechanism","volume":"254","author":"Wang","year":"2024","journal-title":"Comput. Netw."},{"key":"10.1016\/j.comnet.2026.112335_bib0064","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Learning differentially private recurrent language models [C]","author":"McMahan","year":"2018"},{"key":"10.1016\/j.comnet.2026.112335_bib0065","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-025-02280-z","article-title":"Differential privacy for medical deep learning: methods, tradeoffs, and deployment implications","author":"Mohammadi","year":"2026","journal-title":"NPJ. Digit. Med."},{"issue":"4","key":"10.1016\/j.comnet.2026.112335_bib0066","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3704633","article-title":"Membership inference attacks and defenses in federated learning: a survey","volume":"57","author":"Bai","year":"2024","journal-title":"ACM. Comput. Surv."},{"key":"10.1016\/j.comnet.2026.112335_bib0067","article-title":"Robust and secure federated learning with verifiable differential privacy","author":"Zhang","year":"2025","journal-title":"IEEe Trans. Dependable Secure Comput."},{"issue":"8","key":"10.1016\/j.comnet.2026.112335_bib0068","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0272766","article-title":"Local differential privacy protection for wearable device data","volume":"17","author":"Li","year":"2022","journal-title":"PLoS. One"},{"issue":"6","key":"10.1016\/j.comnet.2026.112335_bib0069","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1038\/s42256-021-00337-8","article-title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","volume":"3","author":"Kaissis","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"10.1016\/j.comnet.2026.112335_bib0073","author":"Rogers"},{"key":"10.1016\/j.comnet.2026.112335_bib0075","article-title":"Security concerns for large language Models: a survey","volume":"95","author":"Li","year":"2025","journal-title":"J. Info. Secur. Appl."},{"key":"10.1016\/j.comnet.2026.112335_bib0076","series-title":"30th USENIX Security Symposium (USENIX Security 21)","first-page":"2633","article-title":"Extracting training data from large language models [C]","author":"Carlini","year":"2021"},{"key":"10.1016\/j.comnet.2026.112335_bib0077","article-title":"Large language model (LLM) for software security: code analysis, malware analysis, reverse engineering","volume":"98","author":"Jelodar","year":"2026","journal-title":"J. Info. Secur. Appl."},{"key":"10.1016\/j.comnet.2026.112335_bib0078","author":"Nasr"},{"key":"10.1016\/j.comnet.2026.112335_bib0079","series-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","first-page":"4479","article-title":"RewardDS: privacy-preserving fine-tuning for large language models via reward-driven data synthesis [C]","author":"Wang","year":"2025"},{"key":"10.1016\/j.comnet.2026.112335_bib0080","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Differentially private learning needs better features (or much more data) [C]","author":"Tramer","year":"2021"},{"key":"10.1016\/j.comnet.2026.112335_bib0081","first-page":"26409","article-title":"Enabling fast differentially private SGD via just-in-time compilation and vectorization","volume":"34","author":"Subramani","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comnet.2026.112335_bib0082","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2022","first-page":"6481","article-title":"Large-scale differentially private BERT [C]","author":"Anil","year":"2022"},{"key":"10.1016\/j.comnet.2026.112335_bib0083","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Differentially private fine-tuning of language models [C]","author":"Yu","year":"2022"},{"key":"10.1016\/j.comnet.2026.112335_bib0084","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Large language models can be strong differentially private learners [C]","author":"Li","year":"2022"},{"key":"10.1016\/j.comnet.2026.112335_bib0085","author":"Ma"},{"key":"10.1016\/j.comnet.2026.112335_bib0086","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"7319","article-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning [C]","author":"Aghajanyan","year":"2021"},{"key":"10.1016\/j.comnet.2026.112335_bib0087","series-title":"International Conference on Machine Learning","first-page":"3192","article-title":"Differentially private optimization on large models at small cost [C]","author":"Bu","year":"2023"},{"key":"10.1016\/j.comnet.2026.112335_bib0088","series-title":"Proceedings of the 2025 Conference of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"3676","article-title":"CluSanT: differentially private and semantically coherent text sanitization [C]","author":"Awon","year":"2025"},{"key":"10.1016\/j.comnet.2026.112335_bib0089","first-page":"76852","article-title":"Flocks of stochastic parrots: differentially private prompt learning for large language models","volume":"36","author":"Duan","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comnet.2026.112335_bib0090","series-title":"Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security","first-page":"2665","article-title":"DP-Forward: fine-tuning and inference on language models with differential privacy in forward pass [C]","author":"Du","year":"2023"},{"key":"10.1016\/j.comnet.2026.112335_bib0091","series-title":"Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security","first-page":"79","article-title":"Not what you've signed up for: compromising real-world LLM-integrated applications with indirect prompt injection [C]","author":"Greshake","year":"2023"},{"key":"10.1016\/j.comnet.2026.112335_bib0092","series-title":"2019 IEEE Symposium on Security and Privacy (SP)","first-page":"656","article-title":"Certified robustness to adversarial examples with differential privacy [C]","author":"Lecuyer","year":"2019"},{"key":"10.1016\/j.comnet.2026.112335_bib0093","author":"Chen"},{"key":"10.1016\/j.comnet.2026.112335_bib0094","series-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1321","article-title":"Synthetic text generation with differential privacy: a simple and practical recipe [C]","author":"Yue","year":"2023"},{"key":"10.1016\/j.comnet.2026.112335_bib0095","series-title":"arXiv preprint","article-title":"SMOTE-DP: improving privacy-utility tradeoff with synthetic data","author":"Zhou","year":"2025"},{"key":"10.1016\/j.comnet.2026.112335_bib0096","series-title":"2024 IEEE International Conference on Big Data (BigData)","first-page":"6289","article-title":"Differentially private synthetic data generation using context-aware GANs [C]","author":"Kotal","year":"2024"},{"key":"10.1016\/j.comnet.2026.112335_bib0097","series-title":"A survey on security and privacy of large multimodal deep learning models: Teaching and learning perspective [C]2024 21st Learning and Technology Conference (L&T)","first-page":"13","author":"Rahman","year":"2024"},{"key":"10.1016\/j.comnet.2026.112335_bib0100","article-title":"Privacy-preserving recommendations with mixture model-based matrix factorization under local differential Privacy","author":"Zhang","year":"2025","journal-title":"IEEe Trans. Industr. Inform."},{"key":"10.1016\/j.comnet.2026.112335_bib0101","author":"Panda"},{"key":"10.1016\/j.comnet.2026.112335_bib0102","article-title":"Zero-knowledge proof-based verifiable decentralized machine learning in communication networks: a comprehensive survey","author":"Xing","year":"2025","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"10.1016\/j.comnet.2026.112335_bib0103","author":"Zhang"},{"issue":"15","key":"10.1016\/j.comnet.2026.112335_bib0104","doi-asserted-by":"crossref","first-page":"8344","DOI":"10.1073\/pnas.1914598117","article-title":"Towards formalizing the GDPR\u2019s notion of singling out","volume":"117","author":"Cohen","year":"2020","journal-title":"Proc. Natl. Acad. Sci."},{"key":"10.1016\/j.comnet.2026.112335_bib0105","first-page":"209","article-title":"Differential privacy: a primer for a non-technical audience","volume":"21","author":"Wood","year":"2018","journal-title":"Vanderbilt. J. Entertain. Technol. Law"},{"key":"10.1016\/j.comnet.2026.112335_bib0106","series-title":"Privacy-enhancing Data De-Identification framework: ISO\/IEC 27559:2022 [S]","year":"2022"},{"key":"10.1016\/j.comnet.2026.112335_bib0107","series-title":"Proceedings of the 2024 ACM SIGSAC Conference on Computer and Communications Security","first-page":"3540","article-title":"Curator attack: when blackbox differential privacy auditing loses its power [C]","author":"Wang","year":"2024"},{"key":"10.1016\/j.comnet.2026.112335_bib0108","series-title":"Findings of the Association for Computational Linguistics: ACL 2025","first-page":"4573","article-title":"Unveiling privacy risks in multi-modal large language models: task-specific vulnerabilities and mitigation challenges [C]","author":"Chen","year":"2025"},{"key":"10.1016\/j.comnet.2026.112335_bib0109","series-title":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","first-page":"2529","article-title":"The limits of word-level differential privacy [C]","author":"Mattern","year":"2022"},{"key":"10.1016\/j.comnet.2026.112335_bib0110","author":"Ni"},{"key":"10.1016\/j.comnet.2026.112335_bib0111","article-title":"Differential privacy has disparate impact on model accuracy","volume":"32","author":"Bagdasaryan","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.comnet.2026.112335_bib0112","first-page":"1083","article-title":"Differential privacy and fairness in decisions and learning: a survey","volume":"3","author":"Fioretto","year":"2022","journal-title":"IEEe Trans. Artif. Intell."},{"key":"10.1016\/j.comnet.2026.112335_bib0113","series-title":"Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining","first-page":"1924","article-title":"Removing disparate impact on model accuracy in differentially private stochastic gradient descent [C]","author":"Xu","year":"2021"},{"key":"10.1016\/j.comnet.2026.112335_bib0114","first-page":"49268","article-title":"Privacy auditing with one (1) training run","volume":"36","author":"Steinke","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comnet.2026.112335_bib0115","series-title":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","first-page":"4732","article-title":"Data poisoning against differentially-private learners: attacks and defenses [C]","author":"Ma","year":"2019"},{"key":"10.1016\/j.comnet.2026.112335_bib0116","author":"Mustaqim"},{"key":"10.1016\/j.comnet.2026.112335_bib0117","unstructured":"Kuntzer J, Kaiser J, M\u00fcller T T, et al. Position: generative AI and differential privacy\u2014A perfect match. 2025."},{"key":"10.1016\/j.comnet.2026.112335_bib0118","article-title":"LDPTrace: locally differentially private trajectory synthesis","author":"Du","year":"2024","journal-title":"IEEe Trans. Knowl. Data Eng."},{"key":"10.1016\/j.comnet.2026.112335_bib0119","doi-asserted-by":"crossref","DOI":"10.1109\/TNSM.2025.3529774","article-title":"Auditable homomorphic-based decentralized collaborative AI with attribute-based differential privacy","author":"Yeh","year":"2025","journal-title":"IEEE Trans. Netw. Serv. Manag."}],"container-title":["Computer Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128626003476?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1389128626003476?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T11:33:52Z","timestamp":1779363232000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1389128626003476"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":113,"alternative-id":["S1389128626003476"],"URL":"https:\/\/doi.org\/10.1016\/j.comnet.2026.112335","relation":{},"ISSN":["1389-1286"],"issn-type":[{"value":"1389-1286","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Differential privacy for data sharing: evolution and full-lifecycle applications in generative AI","name":"articletitle","label":"Article Title"},{"value":"Computer Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.comnet.2026.112335","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"112335"}}