On the realness of people who do not exist: The social processing of artificial faces
Source record
tucciarelli-2022-realness· 2022 · iScience
Evidence tier: B (peer-reviewed-journal) · Verification: unverified (compiler confidence: medium)
Bottom line: GAN faces were judged as real as, or more real than, real faces; faces rated more trustworthy were more often judged real.
Citation
Raffaele Tucciarelli, Neza Vehar, Shamil Chandaria, Manos Tsakiris (2022). On the realness of people who do not exist: The social processing of artificial faces. iScience, 25.
Verification entry (identifiers, resolvers, claims with source locations): /data/citations.json#tucciarelli-2022-realness
Study design
| Field | Value |
|---|---|
| Design | Real-vs-artificial classification plus social trait ratings (incl. trustworthiness) |
| Modality | image-face |
| Stimuli | StyleGAN-family faces vs real faces |
| Participants (N) | not recorded |
| N detail | not recorded |
| Topics | human-detection, hyperrealism, trust |
Results
| Metric | Value | Note |
|---|---|---|
| Realness classification | near chance; artificial often judged real | |
| Trust-realness link | positive | more trustworthy → more likely judged real |
Limitations
- Details pending verification
Cited in
- MR-0001: Human Detection of Deepfakes: Accuracy, Bias, Confidence, and Training
Verification
| Field | Value |
|---|---|
| Status | unverified |
| Compiler confidence | medium |
| Checked on | — |
| Via | compiler knowledge; DOI unknown |
Values on this page have not all been checked against the full text. Confirm them against the primary source before high-stakes use.