---
type: source
id: moshel-2022-decoding-ai-faces
title: Are you for real? Decoding realistic AI-generated faces from neural activity
authors:
- Michoel L. Moshel
- Amanda K. Robinson
- Thomas A. Carlson
- Tijl Grootswagers
year: 2022
venue: Vision Research
volume: '199'
pages: '108079'
doi: 10.1016/j.visres.2022.108079
peer_review: peer-reviewed-journal
evidence_tier: B
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
n_participants: null
n_note: not in abstract
topics:
- uncanny-valley
- neural
- implicit-detection
- human-detection
summary: 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.
results:
- metric: Behavioural real-vs-AI judgments
  value: near chance at group level
  note: frequent label swaps; ≈37% figure in press coverage not checked
  source_location: null
- metric: EEG decoding of real vs AI
  value: reliable (above chance)
  note: ≈54% figure in press coverage not checked
  source_location: null
moderators: []
limitations:
- Decoding ≠ conscious or affective response
- Sample sizes not checked
mechanism_supported:
- implicit-sensitivity
verification:
  status: verified-abstract
  confidence: high
  checked: 2026-10-07
  via: Semantic Scholar API abstract
url: null
pmid: null
pmcid: null
arxiv_id: null
openalex_id: null
oa_url: null
cited_in:
- MR-0001
- MR-0002
updated: '2026-10-07'
---

# 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 {#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](/data/citations.json#moshel-2022-decoding-ai-faces)

## Study design {#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 {#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 {#mechanism}

`implicit-sensitivity`

## Limitations {#limitations}

- Decoding ≠ conscious or affective response
- Sample sizes not checked

## Cited in {#cited-in}

- [MR-0001](/metareports/human-detection-accuracy.md): Human Detection of Deepfakes: Accuracy, Bias, Confidence, and Training
- [MR-0002](/metareports/uncanny-valley-and-synthetic-faces.md): The Uncanny Valley and Synthetic Media: Does It Exist, What Causes It, and Have Deepfakes Crossed It?

## Verification {#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.