Article

AI-generated face detection: Why super-recognisers succeed where others fail

2024-11-27

Abstract excerpt

<p>AI-generated faces have become virtually indistinguishable from real human faces. In this study, we demonstrate that super-recognisers—individuals with exceptional face recognition abilities—can reliably detect AI-generated faces, while typical observers cannot. Super-recognisers (N=36) and typical observers (N=89) were shown images of real and AI-generated faces and classified each as real or fake. Super-recog...

Topics

Open a Topic to create a Post that cites this publication.

dental development and anomalies

Identifiers and source

Literature Corpus work: a9b4b6c4-a13d-5146-818a-76b38ad7be57
DOI: 10.31234/osf.io/fwjsb

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

AI-generated face detection: Why super-recognisers succeed where others failDOI 10.31234/osf.io/fwjsbRead

Human Detection of AI-Generated Faces and Voices is Not Domain-GeneralSemantic proximity Read

Seeing is Deceiving: The Psychology and Neuroscience of Fake FacesSemantic proximity Read

Voice clones sound realistic but not (yet) hyperrealisticSemantic proximity Read

Deepfake Detection in Super-Recognizers and Police OfficersSemantic proximity Read

Perceived Artificiality Markedly Reduces Trustworthiness but Only Minimally Affects Attractiveness in AI-Synthetic FacesSemantic proximity Read

Synthetic And Natural Face Identity Processing Share Common MechanismsSemantic proximity Read

Training super-recognisers’ detection and discrimination of computer-generated facesSemantic proximity Read

Benchmarking Automation-Aided Performance in a Forensic Face Matching TaskSemantic proximity Read