{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:03:30Z","timestamp":1781021010007,"version":"3.54.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82474394"],"award-info":[{"award-number":["82474394"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272328"],"award-info":[{"award-number":["62272328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2024ZD0608200"],"award-info":[{"award-number":["2024ZD0608200"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education in China (MOE) Liberal Arts and Social Sciences Foundation","award":["24XJCZH004"],"award-info":[{"award-number":["24XJCZH004"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M752210"],"award-info":[{"award-number":["2024M752210"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan University Postdoctoral Interdisciplinary Innovation Fund"},{"name":"Sichuan Science and Technology Program","award":["2024NSFJQ0026"],"award-info":[{"award-number":["2024NSFJQ0026"]}]},{"name":"Key Research and Development Program of Sichuan Province, China","award":["2023YFG0115"],"award-info":[{"award-number":["2023YFG0115"]}]},{"name":"Key Research and Development Program of Sichuan Province, China","award":["2023YFG0112"],"award-info":[{"award-number":["2023YFG0112"]}]},{"name":"Basic Research Projects of Sichuan Provincial Industrial Development Fund: \u201cContainer Cloud Computing Infrastructure Platform\u201d","award":["2023JB03"],"award-info":[{"award-number":["2023JB03"]}]},{"name":"\u201cNext-Generation Big Data Visualization Based Decision-Making and Analysis Platform\u201d","award":["2023JB06"],"award-info":[{"award-number":["2023JB06"]}]},{"name":"Cooperative Program of Sichuan University and Zigong, China","award":["2022CDZG-6"],"award-info":[{"award-number":["2022CDZG-6"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tifs.2025.3613955","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T17:32:53Z","timestamp":1758735173000},"page":"10391-10404","source":"Crossref","is-referenced-by-count":2,"title":["Improving Privacy Budget Auditing of Differentially Private Artificial Intelligence Models Through Variance of Model Parameters"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5040-8125","authenticated-orcid":false,"given":"Weixin","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7682-4354","authenticated-orcid":false,"given":"Wen","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhishuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Software and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingxuan","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8396-6825","authenticated-orcid":false,"given":"Wenzheng","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5831-2240","authenticated-orcid":false,"given":"Jian","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3139-8528","authenticated-orcid":false,"given":"Yongjian","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Information Software and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3014246"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599561"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103349"},{"key":"ref4","first-page":"23681","article-title":"Differential privacy has bounded impact on fairness in classification","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Mangold"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2023.3320758"},{"key":"ref6","first-page":"1","article-title":"Dynamic personalized federated learning with adaptive differential privacy","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3400312"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3640312"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3312118"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417282"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LICS52264.2021.9470708"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14778\/3055330.3055331"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616607"},{"key":"ref14","article-title":"Diffprivlib: The IBM differential privacy library","author":"Holohan","year":"2019","journal-title":"arXiv:1907.02444"},{"key":"ref15","article-title":"Opacus: User-friendly differential privacy library in PyTorch","author":"Yousefpour","year":"2021","journal-title":"arXiv:2109.12298"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36594-2_24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00069"},{"key":"ref18","first-page":"4165","article-title":"A general framework for auditing differentially private machine learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref19","first-page":"22205","article-title":"Auditing differentially private machine learning: How private is private SGD?","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Jagielski"},{"key":"ref20","article-title":"CANIFE: Crafting canaries for empirical privacy measurement in federated learning","author":"Maddock","year":"2022","journal-title":"arXiv:2210.02912"},{"key":"ref21","first-page":"66201","article-title":"Unleashing the power of randomization in auditing differentially private ML","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pillutla"},{"key":"ref22","article-title":"One-shot empirical privacy estimation for federated learning","author":"Andrew","year":"2023","journal-title":"arXiv:2302.03098"},{"key":"ref23","first-page":"49268","article-title":"Privacy auditing with one training run","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Steinke"},{"key":"ref24","first-page":"289","article-title":"Privacy-preserving logistic regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"21","author":"Chaudhuri"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.14778\/2350229.2350253"},{"issue":"1","key":"ref26","first-page":"1309","article-title":"Differential privacy preservation for deep auto-encoders: An application of human behavior prediction","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"30","author":"Phan"},{"key":"ref27","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128756","article-title":"Auditing privacy budget of differentially private neural network models","volume":"614","author":"Huang","year":"2025","journal-title":"Neurocomputing"},{"key":"ref28","article-title":"Gradient perturbation is underrated for differentially private convex optimization","author":"Yu","year":"2019","journal-title":"arXiv:1911.11363"},{"key":"ref29","first-page":"1895","article-title":"Evaluating differentially private machine learning in practice","volume-title":"Proc. 28th USENIX Secur. Symp. (USENIX Security)","author":"Jayaraman"},{"key":"ref30","article-title":"Nearly tight black-box auditing of differentially private machine learning","author":"Annamalai","year":"2024","journal-title":"arXiv:2405.14106"},{"key":"ref31","article-title":"Adversarial sample-based approach for tighter privacy auditing in final model-only scenarios","author":"Yoon","year":"2025","journal-title":"arXiv:2412.01756"},{"key":"ref32","first-page":"1631","article-title":"Tight auditing of differentially private machine learning","volume-title":"Proc. 32nd USENIX Secur. Symp. (USENIX Security)","author":"Nasr"},{"key":"ref33","first-page":"21","article-title":"Evaluating the usability of differential privacy tools with data practitioners","volume-title":"Proc. 20th Symp. Usable Privacy Secur. (SOUPS)","author":"Ngong"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1561\/0400000042"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CSF.2017.11"},{"key":"ref36","article-title":"R\u00e9nyi differential privacy of the sampled Gaussian mechanism","author":"Mironov","year":"2019","journal-title":"arXiv:1908.10530"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref38","volume-title":"Acquire Valued Shoppers Challenge","year":"2020"},{"key":"ref39","article-title":"An empirical study on the intrinsic privacy of SGD","author":"Hyland","year":"2019","journal-title":"arXiv:1912.02919"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/10810755\/11178103.pdf?arnumber=11178103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:37:01Z","timestamp":1759945021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11178103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/tifs.2025.3613955","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}