Tagged photos

Proceedings of the 2022 International Conference on Advanced Visual Interfaces

Farzand

Mumm

et al. 2022

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. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

Section: Related Work 21 Obfuscating Individuals In Photosmentioning

confidence: 88%

Section: Related Work 21 Obfuscating Individuals In Photosmentioning

confidence: 99%

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

Proceedings of the 2022 International Conference on Advanced Visual Interfaces

Farzand

Mumm

et al. 2022

“…They recommended inpainting individuals or replacing them with avatars because these obfuscation methods provided a good trade-off between effective protection of privacy against computer vision attacks and a good viewer experience [37]. However, they also reported that blurring was among the preferred techniques, conforming with its extensive usage in research and practice [5,28,36]. Gross et al showed that blurring and pixelating of human faces could extensively expose features hindering privacy, or extensively eliminate features hindering the utility of videos [20].…”

Section: Privacy In Lifelogsmentioning

confidence: 99%

Impact of Privacy Protection Methods of Lifelogs on Remembered Memories

Elagroudy

Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

Mathis

et al. 2023

“…C2 (obfuscation) Participants received an obfuscated version of photos in (C1), where all persons were blurred (see sidebar 1). We used body blurring because of positive results in prior work [2,8,12] and its wide adoption in research and industry (e.g. Google Maps).…”

Section: Session 1: Building the Lifelog In A Controlled Eventmentioning

confidence: 99%

Can Privacy-Aware Lifelogs Alter Our Memories?

Elagroudy

Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems

Mathis

et al. 2019

The abundance of automatically-triggered lifelogging cameras is a privacy threat to bystanders. Countering this by deleting photos limits relevant memory cues and the informative content of lifelogs. An alternative is to obfuscate bystanders, but it is not clear how this impacts the lifelogger's recall of memories. We report on a study in which we compare viewing 1) unaltered photos, 2) photos with blurred people, and 3) a subset of the photos after deleting private ones, on memory recall. Findings show that obfuscated content helps users recall a lot of content, but it also results in recalling less accurate details, which can sometimes mislead the user. Our work informs the design of privacyaware lifelogging systems that maximizes recall and steers discussion about ubiquitous technologies that could alter human memories.