TY - CHAP AU - Gulyás, Gábor György AU - Gönczy, László AU - Kocsis, Imre AU - Magyar, Gábor AU - Papp, Dávid AU - Szűcs, Gábor ED - Magyar, Gábor ED - Nemeslaki, András ED - Szakadát, István TI - Digitális lábnyomok és hatásuk a pénzügyi rendszerre T2 - A digitális transzformáció technológiai kérdései PB - Gondolat Kiadó CY - Budapest SN - 9789635561988 PY - 2021 SP - 19 EP - 171 PG - 153 UR - https://m2.mtmt.hu/api/publication/32546390 ID - 32546390 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Fábián, István AU - Gulyás, Gábor György TI - A Comparative Study on the Privacy Risks of Face Recognition Libraries JF - ACTA CYBERNETICA J2 - ACTA CYBERN-SZEGED VL - 25 PY - 2021 IS - 2 SP - 233 EP - 255 PG - 23 SN - 0324-721X DO - 10.14232/actacyb.289662 UR - https://m2.mtmt.hu/api/publication/32532422 ID - 32532422 N1 - Export Date: 2 May 2022 CODEN: ACCYD LA - English DB - MTMT ER - TY - BOOK AU - Fábián, István AU - Gulyás, Gábor György TI - Risk Mitigation of Facial Recognition PB - Budapesti Műszaki Egyetem, Automatizálási és Alkalmazott Informatikai Tanszék CY - Budapest PY - 2021 UR - https://m2.mtmt.hu/api/publication/32038979 ID - 32038979 LA - English DB - MTMT ER - TY - CHAP AU - Fábián, István AU - Gulyás, Gábor György AU - Kiséry, Máté Soma ED - Dunaev, Dmitriy ED - Gulyás, Gábor György ED - Vajk, István TI - Analysis of Demographic Attributes of Face Imprints T2 - Proceedings of the Automation and Applied Computer Science Workshop 2020 PB - Budapesti Műszaki és Gazdaságtudományi Egyetem, Villamosmérnöki és Informatikai Kar CY - Budapest SN - 9789634218166 PY - 2020 SP - 136 EP - 145 PG - 10 UR - https://m2.mtmt.hu/api/publication/31721503 ID - 31721503 LA - English DB - MTMT ER - TY - JOUR AU - Fábián, István AU - Gulyás, Gábor György TI - De-anonymizing Facial Recognition Embeddings JF - INFOCOMMUNICATIONS JOURNAL J2 - INFOCOMM J VL - 12 PY - 2020 IS - 2 SP - 50 EP - 56 PG - 7 SN - 2061-2079 DO - 10.36244/ICJ.2020.2.7 UR - https://m2.mtmt.hu/api/publication/31615403 ID - 31615403 N1 - Cited By :3 Export Date: 14 June 2022 AB - Advances of machine learning and hardware getting cheaper resulted in smart cameras equipped with facial recognition becoming unprecedentedly widespread worldwide. Undeniably, this has a great potential for a wide spectrum of uses, it also bears novel risks. In our work, we consider a specific related risk, one related to face embeddings, which are machine learning created metric values describing the face of a person. While embeddings seems arbitrary numbers to the naked eye and are hard to interpret for humans, we argue that some basic demographic attributes can be estimated from them and these values can be then used to look up the original person on social networking sites. We propose an approach for creating synthetic, life-like datasets consisting of embeddings and demographic data of several people. We show over these ground truth datasets that the aforementioned re-identifications attacks do not require expert skills in machine learning in order to be executed. In our experiments, we find that even with simple machine learning models the proportion of successfully re-identified people vary between 6.04% and 28.90%, depending on the population size of the simulation. LA - English DB - MTMT ER - TY - BOOK ED - Dunaev, Dmitriy ED - Gulyás, Gábor György ED - Vajk, István TI - Proceedings of the Automation and Applied Computer Science Workshop 2020. AACS’20 TS - AACS’20 PB - Budapesti Műszaki és Gazdaságtudományi Egyetem, Villamosmérnöki és Informatikai Kar CY - Budapest PY - 2020 SN - 9789634218166 UR - https://m2.mtmt.hu/api/publication/31522823 ID - 31522823 LA - English DB - MTMT ER - TY - CONF AU - Fábián, István AU - Gulyás, Gábor György TI - On the Privacy Risks of Large-Scale Processing of Face Imprints T2 - The 12th Conference of PhD Students in Computer Science PB - Szegedi Tudományegyetem (SZTE) C1 - Szeged PY - 2020 SP - 92 EP - 95 PG - 4 UR - https://m2.mtmt.hu/api/publication/31331712 ID - 31331712 AB - As technology advances, the number of applications relying on face recognition is on the rise. While facial recognition technologies have many benefits, it's important to use them in a responsible manner in order to avoid privacy risks. In this paper we analyze the privacy risks of the processing of face imprints generated by face recognition technologies. We characterize the risks of re-identification attacks against facial imprint databases in multiple scenarios regarding different attacker strength. Our findings show that even if a large number of subjects are surveilled and the attacker can only inefficiently benefit from using the embeddings, the risk of re-identification is still concerning. LA - English DB - MTMT ER - TY - JOUR AU - Gulyás, Gábor György AU - Imre, Sándor TI - Hiding information against structural re-identification JF - INTERNATIONAL JOURNAL OF INFORMATION SECURITY J2 - INT J INF SECUR VL - 18 PY - 2019 IS - 2 SP - 125 EP - 132 PG - 8 SN - 1615-5262 DO - 10.1007/s10207-018-0400-x UR - https://m2.mtmt.hu/api/publication/3334200 ID - 3334200 N1 - Export Date: 28 March 2024 Correspondence Address: Gulyás, G.G.; Privatics Team, France; email: gabor.gulyas@inria.fr LA - English DB - MTMT ER - TY - CHAP AU - Gulyás, Gábor György AU - Some, Doliere Francis AU - Bielova, Nataliia AU - Castelluccia, Claude TI - To Extend or not to Extend: On the Uniqueness of Browser Extensions and Web Logins T2 - Proceedings of the 2018 Workshop on Privacy in the Electronic Society - WPES'18 SN - 9781450359894 PY - 2018 SP - 14 EP - 27 PG - 13 DO - 10.1145/3267323.3268959 UR - https://m2.mtmt.hu/api/publication/30404719 ID - 30404719 N1 - ACM SIGSAC Conference code: 141180 Cited By :25 Export Date: 5 April 2024 Funding details: Agence Nationale de la Recherche, ANR, AJACS ANR-14-CE28-0008, CISC ANR-17-CE25-0014-01 Funding text 1: First of all, we would like to thank the valuable comments and suggestions of the anonymous reviewers of our paper. This research has been partially supported by the ANR projects AJACS ANR-14-CE28-0008 and CISC ANR-17-CE25-0014-01. We are grateful for Alexander Sjösten, Steven Van Acker, Andrei Sabelfeld, who shared their code and signature database for Chrome browser extension detection [56], and also for Robin Linus, who allowed us to build on his script on social media presence detection. We thank Imane Fouad and Natasa Sarafijanovic-Djukic for their help in evaluating the effect of browser extensions on third-party cookies. LA - English DB - MTMT ER - TY - JOUR AU - Gulyás, Gábor György TI - Gépi tanulási módszerek alkalmazása deanonimizálásra JF - INFORMÁCIÓS TÁRSADALOM: TÁRSADALOMTUDOMÁNYI FOLYÓIRAT J2 - INF TARS VL - 7 PY - 2017 IS - 1 SP - 72 EP - 86 PG - 15 SN - 1587-8694 DO - 10.22503/inftars.XVII.2017.1.5 UR - https://m2.mtmt.hu/api/publication/27473218 ID - 27473218 N1 - Export Date: 16 April 2024 Correspondence Address: György, G.G.; BME Villamosmérnöki és Informatikai Karán Szerzett Diplomát, Hungary LA - Hungarian DB - MTMT ER -