Unique traits, computational insights: studying Super-Recognizers for societal applications DOI Open Access
Meike Ramon

Published: Nov. 29, 2023

Nearly fifteen years ago, the term Super-Recognizer (SR) was introduced in scientific literature as a result of an accidental finding. Since then, there has been surging interest topic — both from within research community, well international media and (mostly European) law enforcement. Given hype hope around SRs, review our current understanding their ability is needed. I findings outline future avenues for SR work, which extend beyond advancing human cognition. The “face recognition” attracts attention various stakeholders, often with opposing views interests, including e.g. NGOs, policy makers, media, industry, who are mostly not involved fundamental research. Therefore, science SRs can serve entry point to facilitate societally relevant discussions, neurodiversity, right privacy security. This opportunity comes responsibility adopt highest standards terms rigor transparency, ensure that high quality, participatory inclusive disseminated honestly broadly.

Language: Английский

The Super‐Recogniser Advantage Extends to the Detection of Digitally Manipulated Faces DOI Creative Commons
Josh P. Davis, David J. Robertson, Ryan Jenkins

et al.

Applied Cognitive Psychology, Journal Year: 2025, Volume and Issue: 39(2)

Published: March 1, 2025

ABSTRACT Face recognition by human officials remains the predominant method of identity verification in security‐critical contexts. The integrity this process can be compromised sophisticated fraud attacks using manipulated face images. Therefore, study, we examine whether observers detect digitally passport photos, and super‐recognisers (SRs) outperform typical recogniser controls. Using two manipulation detection tasks (DFMD1, DFMD2), participants were asked to decide a ‘suspected’ photo had been manipulated. SRs found significantly controls; effect was not result ‘speed‐accuracy trade‐off’. Individual differences on tests identification aptitude, self‐rated ability, response times, accounted for over 20% variance image sensitivity. Taken together, these findings show that, despite increasing sophistication digital techniques, there is still utility employing operators, particularly SRs, them.

Language: Английский

Citations

0
Human Versus Machine: A Comparative Analysis in Detecting Artificial Intelligence-Generated Images DOI Creative Commons
Luca Maiano, Alexandra Benova, Lorenzo Papa

et al.

IEEE Security & Privacy, Journal Year: 2024, Volume and Issue: 22(3), P. 77 - 86

Published: May 1, 2024

This article delves into the intricate process of artificial intelligence-generated content detection, shedding light on automated detectors' challenges and revealing human detection biases, strengths, weaknesses.

Language: Английский

Citations

2
SYNTHETIC AND NATURAL FACE IDENTITY PROCESSING SHARE COMMON MECHANISMS DOI Creative Commons
Kim Uittenhove, Hatef Otroshi Shahreza, Sébastien Marcel

et al.

Computers in Human Behavior Reports, Journal Year: 2024, Volume and Issue: unknown, P. 100563 - 100563

Published: Dec. 1, 2024

Language: Английский

Citations

1
Synthetic And Natural Face Identity Processing Share Common Mechanisms DOI Creative Commons
Kim Uittenhove, Hatef Otroshi Shahreza, Sébastien Marcel

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 6, 2024

Abstract Recent developments in generative AI offer the means to create synthetic identities, or deepfakes, at scale. As deepfake faces and voices become indistinguishable from real ones, they are considered as promising alternatives for research development enhance fairness protect humans’ rights privacy. Notwithstanding these efforts intentions, a basic question remains unanswered: Are natural facial deepfakes perceived remembered same way? Using images created via professional photography on one hand, state-of-the-art model other, we investigated most studied process of face cognition: perceptual matching discrimination identity. Our results demonstrate that identity is governed by underlying mechanisms: objective stimulus similarity observers’ ability level. These findings provide empirical support both societal risks associated with while also underscoring utility identities development.

Language: Английский

Citations

0
Synthetic Realities and Artificial Intelligence-Generated Contents DOI Open Access
Daniel Moreira, Sébastien Marcel, Anderson Rocha

et al.

IEEE Security & Privacy, Journal Year: 2024, Volume and Issue: 22(3), P. 7 - 10

Published: May 1, 2024

Welcome to the IEEE Security & Privacy Special Issue on Synthetic Realities and Artificial Intelligence-Generated Contents! In this edition, we delve into topic of synthetic realities, where generative artificial intelligence (GAI) is revolutionizing construction narratives, blurring boundaries between fact fiction, for good bad. Indeed, content created or enabled by GAI spans a wide spectrum usage intentions, from fostering positive experiences, such as entertainment, training, education, more questionable utilization, deception, propaganda, manipulation.

Language: Английский

Citations

0
Unique traits, computational insights: studying Super-Recognizers for societal applications DOI Open Access
Meike Ramon

Published: Nov. 29, 2023

Nearly fifteen years ago, the term Super-Recognizer (SR) was introduced in scientific literature as a result of an accidental finding. Since then, there has been surging interest topic — both from within research community, well international media and (mostly European) law enforcement. Given hype hope around SRs, review our current understanding their ability is needed. I findings outline future avenues for SR work, which extend beyond advancing human cognition. The “face recognition” attracts attention various stakeholders, often with opposing views interests, including e.g. NGOs, policy makers, media, industry, who are mostly not involved fundamental research. Therefore, science SRs can serve entry point to facilitate societally relevant discussions, neurodiversity, right privacy security. This opportunity comes responsibility adopt highest standards terms rigor transparency, ensure that high quality, participatory inclusive disseminated honestly broadly.

Language: Английский

Citations

0