A comparative study on the privacy risks of face recognition libraries

Fábián István and Gulyás Gábor György: A comparative study on the privacy risks of face recognition libraries. In: Acta cybernetica, (25) 2. pp. 233-255. (2021)

Cikk, tanulmány, mű cybernetica_025_numb_002_233-255.pdf Download (431kB)

Abstract

The rapid development of machine learning and the decreasing costs of computational resources has led to a widespread usage of face recognition. While this technology offers numerous benefits, it also poses new risks. We consider risks related to the processing of face embeddings, which are floating point vectors representing the human face in an identifying way. Previously, we showed that even simple machine learning models are capable of inferring demographic attributes from embeddings, leading to the possibility of re-identification attacks. This paper examines three popular Python libraries for face recognition, comparing their face detection performance and inspecting how much risk each library's embeddings pose regarding the aforementioned data leakage. Our experiments were conducted on a balanced face image dataset of different sexes and races, allowing us to discover biases in our results.

Item Type:	Article
Journal or Publication Title:	Acta cybernetica
Date:	2021
Volume:	25
Number:	2
ISSN:	0324-721X
Page Range:	pp. 233-255
Language:	English
Publisher:	University of Szeged, Institute of Informatics
Place of Publication:	Szeged
Event Title:	Conference of PhD Students in Computer Science (12.) (2020) (Szeged)
Related URLs:	http://acta.bibl.u-szeged.hu/75565/
DOI:	10.14232/actacyb.289662
Uncontrolled Keywords:	Arcfelismerés, Gépi tanulás, Programozás, Adatvédelem
Additional Information:	Bibliogr.: p. 252-255. ; ill. ; összefoglalás angol nyelven
Subjects:	01. Natural sciences 01. Natural sciences > 01.02. Computer and information sciences
Date Deposited:	2022. May. 12. 14:37
Last Modified:	2022. May. 12. 14:37
URI:	http://acta.bibl.u-szeged.hu/id/eprint/75608

Actions (login required)

View Item