Are you for real? Decoding realistic AI-generated faces from neural activity

Source record moshel-2022-decoding-ai-faces · 2022 · Vision Research
Evidence tier: B (peer-reviewed-journal) · Verification: verified-abstract (compiler confidence: high)
Bottom line: Group-level behavioural judgments were near chance (people often called real faces fake and vice versa), yet neural activity reliably distinguished AI-generated from real faces.

Citation

Michoel L. Moshel, Amanda K. Robinson, Thomas A. Carlson, Tijl Grootswagers (2022). Are you for real? Decoding realistic AI-generated faces from neural activity. Vision Research, 199, 108079. https://doi.org/10.1016/j.visres.2022.108079

Verification entry (identifiers, resolvers, claims with source locations): /data/citations.json#moshel-2022-decoding-ai-faces

Study design

Field	Value
Design	Behavioural real-vs-AI classification plus EEG multivariate decoding of real vs AI faces
Modality	image-face
Stimuli	Realistic GAN faces vs real faces
Participants (N)	not recorded
N detail	not in abstract
Topics	uncanny-valley, neural, implicit-detection, human-detection

Results

Metric	Value	Note
Behavioural real-vs-AI judgments	near chance at group level	frequent label swaps; ≈37% figure in press coverage not checked
EEG decoding of real vs AI	reliable (above chance)	≈54% figure in press coverage not checked

Mechanism relevance

implicit-sensitivity

Limitations

Decoding ≠ conscious or affective response
Sample sizes not checked

Cited in

MR-0001: Human Detection of Deepfakes: Accuracy, Bias, Confidence, and Training
MR-0002: The Uncanny Valley and Synthetic Media: Does It Exist, What Causes It, and Have Deepfakes Crossed It?

Verification

Field	Value
Status	`verified-abstract`
Compiler confidence	high
Checked on	2026-10-07
Via	Semantic Scholar API abstract

Values on this page have not all been checked against the full text. Confirm them against the primary source before high-stakes use.