DeepFakes for Privacy: Investigating Perceptions and Effectiveness of State-of-the-Art Privacy-Enhancing Face Obfuscation Methods

Khamis, M. , Farzand, H., Mumm, M. and Marky, K. (2022) DeepFakes for Privacy: Investigating Perceptions and Effectiveness of State-of-the-Art Privacy-Enhancing Face Obfuscation Methods. In: 2022 International Conference on Advanced Visual Interfaces (AVI 2022), Rome, Italy, 06-10 Jun 2022, p. 21. ISBN 9781450397193 (doi: 10.1145/3531073.3531125)

[img] Text
269740.pdf - Accepted Version

736kB

Abstract

There are many contexts in which a person’s face needs to be obfuscated for privacy, such as in social media posts. We present a user-centered analysis of the effectiveness of DeepFakes for obfuscation using synthetically generated faces, and compare it with state-of-the-art obfuscation methods: blurring, masking, pixelating, and replacement with avatars. For this, we conducted an online survey (N=110) and found that DeepFake obfuscation is a viable alternative to state-of-the-art obfuscation methods; it is as effective as masking and avatar obfuscation in concealing the identities of individuals in photos. At the same time, DeepFakes blend well with surroundings and are as aesthetically pleasing as blurring and pixelating. We discuss how DeepFake obfuscation can enhance privacy protection without negatively impacting the photo’s aesthetics.

Item Type:Conference Proceedings
Additional Information:This work was supported an EPSRC New Investigator Award (grant number EP/V008870/1), and by the PETRAS National Centre of Excellence for IoT Systems Cybersecurity, which has also been funded by the UK EPSRC under grant number EP/S035362/1. This publication was partially supported by the Excellence Bursary Award by the University of Glasgow.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Marky, Dr Karola and Mumm, Marija and Farzand, Ms Habiba and Khamis, Dr Mohamed
Authors: Khamis, M., Farzand, H., Mumm, M., and Marky, K.
College/School:College of Science and Engineering > School of Computing Science
ISBN:9781450397193
Copyright Holders:Copyright © 2022 ACM
First Published:First published in AVI 2022, Article 21
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
310627TAPS: Assessing, Mitigating and Raising Awareness of the Security and Privacy Risks of Thermal ImagingMohamed KhamisEngineering and Physical Sciences Research Council (EPSRC)EP/V008870/1Computing Science