Does the ‘super recogniser’ advantage extend to the detection of digitally manipulated faces?

Tools

Busch, Christoph and Davis, Josh P. and Robertson, David J. and Jenkins, Ryan E. and Ibsen, Mathias and Nichols, Robert and Babbs, Martha and Rathgeb, Christian and Løvåsdal, Frøy and Raja, Kiran (2024) Does the ‘super recogniser’ advantage extend to the detection of digitally manipulated faces? In: Combatting ID Fraud, 2024-11-21 - 2024-11-21.

[thumbnail of Busch-etal-iMARS-2024-Does-the-super-recogniser-advantage-extend-to-the-detection-of-digitally-manipulated-faces]
Preview
 Text. Filename: Busch-etal-iMARS-2024-Does-the-super-recogniser-advantage-extend-to-the-detection-of-digitally-manipulated-faces.pdf
Final Published Version
License: Strathprints license 1.0
Download (2MB)| Preview

Abstract

Face recognition by human officials remains the predominant method of identity verification in security-critical contexts (e.g., passport renewal, border control). The integrity of this process can be compromised by sophisticated fraud attacks using digitally manipulated face images. In this study we examine whether human observers can robustly detect digitally manipulated passport photos and whether super-recognisers (SRs), individuals who excel at identity recognition, outperform typical recogniser controls. Here, we present some findings from the initial analysis.

ORCID iDs

Busch, Christoph, Davis, Josh P., Robertson, David J. ORCID logoORCID: https://orcid.org/0000-0002-8393-951X, Jenkins, Ryan E., Ibsen, Mathias, Nichols, Robert, Babbs, Martha, Rathgeb, Christian, Løvåsdal, Frøy and Raja, Kiran;
CORE (COnnecting REpositories)