{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:02:13Z","timestamp":1764784933640,"version":"3.37.3"},"reference-count":58,"publisher":"EDP Sciences","license":[{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"vor","delay-in-days":205,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National Key Research and Development Program of \u2028China","award":["grant number 2018YFB2100801"],"award-info":[{"award-number":["grant number 2018YFB2100801"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Security and Safety","S&amp;S"],"accepted":{"date-parts":[[2022,6,16]]},"published-print":{"date-parts":[[2022]]},"abstract":"<jats:p>This paper addresses a special and imperceptible class of privacy, called implicit privacy. In contrast to traditional (explicit) privacy, implicit privacy has two essential properties: (1) It is not initially defined as a privacy attribute; (2) it is strongly associated with privacy attributes. In other words, attackers could utilize it to infer privacy attributes with a certain probability, indirectly resulting in the disclosure of private information. To deal with the implicit privacy disclosure problem, we give a measurable definition of implicit privacy, and propose an ex-ante implicit privacy-preserving framework based on data generation, called IMPOSTER. The framework consists of an implicit privacy detection module and an implicit privacy protection module. The former uses normalized mutual information to detect implicit privacy attributes that are strongly related to traditional privacy attributes. Based on the idea of data generation, the latter equips the Generative Adversarial Network (GAN) framework with an additional discriminator, which is used to eliminate the association between traditional privacy attributes and implicit ones. We elaborate a theoretical analysis for the convergence of the framework. Experiments demonstrate that with the learned generator, IMPOSTER can alleviate the disclosure of implicit privacy while maintaining good data utility.<\/jats:p>","DOI":"10.1051\/sands\/2022008","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T07:55:45Z","timestamp":1658735745000},"page":"2022008","source":"Crossref","is-referenced-by-count":2,"title":["Implicit privacy preservation: a framework based on data generation"],"prefix":"10.1051","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5092-5437","authenticated-orcid":false,"given":"Qing","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4752-0316","authenticated-orcid":false,"given":"Cheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4946-8977","authenticated-orcid":false,"given":"Teng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0391-9376","authenticated-orcid":false,"given":"Xue","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0637-9317","authenticated-orcid":false,"given":"Changjun","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"250","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"key":"R1","unstructured":"Han J, Pei J and Kamber M. Data Mining: Concepts and Techniques. The Netherlands: Elsevier, 2011."},{"key":"R2","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1038\/s41586-020-2284-y","volume":"582","author":"Jia","year":"2020","journal-title":"Nature"},{"key":"R3","doi-asserted-by":"crossref","first-page":"2995","DOI":"10.1109\/TKDE.2019.2959988","volume":"33","author":"Park","year":"2021","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"R4","first-page":"13396","volume":"34","author":"Wang","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"R5","doi-asserted-by":"crossref","unstructured":"Liu Y, Ao X and Zhong Q et al. Alike and unlike: Resolving class imbalance problem in financial credit risk assessment. In: Proc. 29th ACM Int. Conf. Inf. Knowl. Manag. Virtual Event, Ireland, Oct. 19-23, 2020, 2125\u20138.","DOI":"10.1145\/3340531.3412111"},{"key":"R6","doi-asserted-by":"crossref","first-page":"536","DOI":"10.1126\/science.1256297","volume":"347","author":"De Montjoye","year":"2015","journal-title":"Science"},{"key":"R7","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1109\/TMM.2021.3073267","volume":"24","author":"Zhang","year":"2022","journal-title":"IEEE Trans Multim"},{"key":"R8","first-page":"4027","volume":"35","author":"Deng","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"R9","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1109\/TKDE.2018.2882404","volume":"32","author":"Hu","year":"2018","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"6","key":"R10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3375752","volume":"23","author":"Wu","year":"2020","journal-title":"ACM Trans Priv Secur"},{"key":"R11","unstructured":"Holt JD and Chung SM. Efficient mining of association rules in text databases. In: Proc. 1999 ACM CIKM Int. Conf. Inf. Knowl. Manag., Kansas City, Missouri, USA, Nov. 2-6, 1999, 234\u201342."},{"key":"R12","doi-asserted-by":"crossref","first-page":"838","DOI":"10.1109\/TIFS.2013.2253320","volume":"8","author":"Sankar","year":"2013","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"R13","doi-asserted-by":"crossref","unstructured":"Narayanan A and Shmatikov V. Robust de-anonymization of large sparse datasets. In: 2008 IEEE Symp. Secur. Priv. (SP), Oakland, CA, USA, May 18-22, 2008, 111\u201325.","DOI":"10.1109\/SP.2008.33"},{"key":"R14","doi-asserted-by":"crossref","unstructured":"Li S, Ji X and You W. A personalized differential privacy protection method for repeated queries. In: 2019 IEEE 4th Int. Conf. Big Data Anal. (ICBDA), Suzhou, China, Mar. 15-18, 2019, 274\u2013280.","DOI":"10.1109\/ICBDA.2019.8713224"},{"key":"R15","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","volume":"9","author":"Dwork","year":"2014","journal-title":"Found Trends Theor Comput Sci"},{"key":"R16","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/1217299.1217302","volume":"1","author":"Machanavajjhala","year":"2007","journal-title":"ACM Trans Knowl Discov Data"},{"key":"R17","doi-asserted-by":"crossref","unstructured":"Li N, Li T and Venkatasubramanian S. t-closeness: Privacy beyond k-anonymity and l-diversity. In: Proc. 23rd Int. Conf. Data Eng., The Marmara Hotel, Istanbul, Turkey, Apr. 15-20, 2007, 106\u201315.","DOI":"10.1109\/ICDE.2007.367856"},{"issue":"12","key":"R18","first-page":"1","volume":"10","author":"Yang","year":"2019","journal-title":"ACM Trans Intell Syst Technol"},{"key":"R19","doi-asserted-by":"crossref","unstructured":"Mohassel P and Zhang Y. Secureml: A system for scalable privacy-preserving machine learning. In: 2017 IEEE Symp. Secur. Priv. (SP), San Jose, CA, USA, May 22-26, 2017, 19\u201338.","DOI":"10.1109\/SP.2017.12"},{"key":"R20","doi-asserted-by":"crossref","unstructured":"Chen H, Dai W and Kim M et al. Efficient multi-key homomorphic encryption with packed ciphertexts with application to oblivious neural network inference. In Proc. 2019 ACM SIGSAC Conf. Comput. Commun. Secur., CCS 2019, London, UK, Nov. 11-15, 2019, 395\u2013412.","DOI":"10.1145\/3319535.3363207"},{"key":"R21","unstructured":"Fredrikson M, Lantz E and Jha S et al. Privacy in pharmacogenetics: An end-to-end case study of personalized warfarin dosing. In: Proc. 23rd USENIX Secur. Symp., San Diego, CA, USA, Aug. 20-22, 2014, 17\u201332."},{"key":"R22","unstructured":"Krause A and Horvitz E. A utility-theoretic approach to privacy and personalization. In: Proc. Twenty-Third AAAI Conf. Artif. Intell., Chicago, Illinois, USA, July 13-17, 2008, Vol. 8, 1181\u20138."},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Gross R, Airoldi E and Malin B et al. Integrating Utility into Face De-identification. Berlin, Heidelberg: Springer, 2006.","DOI":"10.1007\/11767831_15"},{"key":"R24","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1109\/TCSS.2020.3035462","volume":"8","author":"Yang","year":"2020","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Datta A, Fredrikson M and Ko G et al. Use privacy in data-driven systems: Theory and experiments with machine learnt programs. In: Proc. 2017 ACM SIGSAC Conf. Comput. Commun. Secur., CCS 2017, Dallas, TX, USA, Oct. 30-Nov. 03, 2017, 1193\u2013210.","DOI":"10.1145\/3133956.3134097"},{"key":"R26","doi-asserted-by":"crossref","first-page":"2499","DOI":"10.1109\/TIFS.2020.2968188","volume":"15","author":"Tseng","year":"2020","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"R27","doi-asserted-by":"crossref","first-page":"1603","DOI":"10.1109\/TITS.2020.2973398","volume":"22","author":"Kim","year":"2020","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"R28","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.neucom.2019.11.116","volume":"416","author":"Ruffino","year":"2020","journal-title":"Neurocomputing"},{"key":"R29","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/j.procs.2019.01.256","volume":"147","author":"Zhang","year":"2019","journal-title":"Proc Comput Sci"},{"key":"R30","unstructured":"Xie L, Lin K and Wang S et al. Differentially private generative adversarial network, arXiv preprint arXiv:1802.06739, 2018."},{"key":"R31","unstructured":"Jordon J, Yoon J and van der Schaar M. PATE-GAN: Generating synthetic data with differential privacy guarantees. In: 7th Int. Conf. Learn. Represent., ICLR 2019, New Orleans, LA, USA, May 6-9, 2019."},{"key":"R32","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1080\/01621459.1965.10480775","volume":"60","author":"Warner","year":"1965","journal-title":"J Am Stat Assoc"},{"key":"R33","doi-asserted-by":"crossref","unstructured":"Aggarwal CC and Philip SY. A Condensation Approach to Privacy Preserving Data Mining. Berlin, Heidelberg: Springer, 2004.","DOI":"10.1007\/978-3-540-24741-8_12"},{"key":"R34","unstructured":"Dwork C. Differential privacy. In: Autom. Lang. Program. 33rd Int. Colloq. ICALP 2006, Venice, Italy, Jul. 10-14, 2006, Proc. Part II, 2006, 1\u201312."},{"key":"R35","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1142\/S0218488502001648","volume":"10","author":"Sweeney","year":"2002","journal-title":"Int J Uncertain Fuzziness Knowl Based Syst"},{"key":"R36","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/j.ins.2018.10.024","volume":"476","author":"Zhao","year":"2019","journal-title":"Inf Sci"},{"key":"R37","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/TIT.1985.1057074","volume":"31","author":"Elgamal","year":"1985","journal-title":"IEEE Trans Inf Theor"},{"key":"R38","first-page":"102366","volume":"48","author":"Ullah","year":"2049","journal-title":"J Inf Secur Appl"},{"key":"R39","first-page":"492","volume":"17","author":"Kairouz","year":"2016","journal-title":"J Mach Learn Res"},{"key":"R40","unstructured":"Goodfellow I, Pouget-Abadie J and Mirza M et al. Generative adversarial nets. In: Adv. Neural Inf. Process. Syst. 27: Annu. Conf. Neural Inf. Process. Syst. 2014, Montreal, Quebec, Canada, Dec. 8-13, 2014, 2672\u20132680."},{"key":"R41","unstructured":"Mirza M and Osindero S. Conditional generative adversarial nets, arXiv preprint arXiv:1411.1784, 2014."},{"key":"R42","doi-asserted-by":"crossref","unstructured":"Torra V. Data Privacy: Foundations, New Developments and the Big Data Challenge. Heidelberg: Springer, 2017.","DOI":"10.1007\/978-3-319-57358-8"},{"key":"R43","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1109\/ACCESS.2014.2362522","volume":"2","author":"Xu","year":"2014","journal-title":"IEEE Access"},{"key":"R44","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1109\/TNN.2008.2005601","volume":"20","author":"Est\u00e9vez","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"R45","doi-asserted-by":"crossref","unstructured":"Jaynes ET. Information theory and statistical mechanics. Phys Rev 1957; 106: 620.","DOI":"10.1103\/PhysRev.106.620"},{"key":"R46","doi-asserted-by":"crossref","unstructured":"Benesty J, Chen J and Huang Y et al. Pearson correlation coefficient. Berlin, Heidelberg: Springer, 2009.","DOI":"10.1007\/978-3-642-00296-0_5"},{"key":"R47","doi-asserted-by":"crossref","unstructured":"Nargesian F, Samulowitz H and Khurana U et al. Learning feature engineering for classification, In: Proc. Twenty-Sixth Int. Jt. Conf. Artif. Intell., IJCAI 2017, Melbourne, Australia, Aug. 19-25, 2017, 2529\u201335.","DOI":"10.24963\/ijcai.2017\/352"},{"key":"R48","doi-asserted-by":"crossref","unstructured":"Datta A, Sen S and Zick Y. Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems. In: 2016 IEEE Symp. Secur. Priv. (SP), San Jose, CA, USA, May 22-26, 2016, 598\u2013617.","DOI":"10.1109\/SP.2016.42"},{"key":"R49","doi-asserted-by":"crossref","first-page":"1385","DOI":"10.1109\/TPAMI.2006.186","volume":"28","author":"Hild II","year":"2006","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"R50","unstructured":"Kingma DP and Welling M. Auto-encoding variational bayes. In: Bengio Y and LeCun Y, editors, 2nd Int. Conf. Learn. Represent., ICLR 2014, Ban, AB, Canada, Apr. 14-16, 2014, Conf. Track Proc., 2014."},{"key":"R51","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0016-0032(96)00063-4","volume":"334","author":"Men\u00e9ndez","year":"1997","journal-title":"J Frankl Inst"},{"key":"R52","doi-asserted-by":"crossref","unstructured":"Chen T and Guestrin C. XGBoost: A scalable tree boosting system. In: Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining, San Francisco, CA, USA, Aug. 13-17, 2016, 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"key":"R53","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"Friedman","year":"2001","journal-title":"Annal Stat"},{"key":"R54","first-page":"4642","volume":"34","author":"Li","year":"2020","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"R55","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"R56","unstructured":"Anthony M and Bartlett PL. Neural Network Learning: Theoretical Foundations. Cambridge: Cambridge University Press, 2009."},{"key":"R57","doi-asserted-by":"crossref","unstructured":"Pan X and Xu Y. A safe feature elimination rule for L1-regularized logistic regression. IEEE Trans Pattern Anal Mach Intell 2021.","DOI":"10.1109\/TPAMI.2021.3071138"},{"key":"R58","doi-asserted-by":"crossref","first-page":"6801","DOI":"10.1109\/TIT.2014.2357799","volume":"60","author":"Fehr","year":"2014","journal-title":"IEEE Trans Inf Theor"}],"container-title":["Security and Safety"],"original-title":[],"link":[{"URL":"https:\/\/sands.edpsciences.org\/10.1051\/sands\/2022008\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T20:11:38Z","timestamp":1727640698000},"score":1,"resource":{"primary":{"URL":"https:\/\/sands.edpsciences.org\/10.1051\/sands\/2022008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":58,"alternative-id":["sands20220006"],"URL":"https:\/\/doi.org\/10.1051\/sands\/2022008","relation":{},"ISSN":["2826-1275"],"issn-type":[{"type":"electronic","value":"2826-1275"}],"subject":[],"published":{"date-parts":[[2022]]}}}