---
type: source
id: cooke-2024-coin-toss
title: 'As good as a coin toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli'
authors:
- Di Cooke
- Abigail Edwards
- Sophia Barkoff
- Kathryn Kelly
year: 2025
venue: Communications of the ACM
volume: '68'
pages: 100-109
doi: 10.1145/3729417
url: https://arxiv.org/abs/2403.16760
arxiv_id: '2403.16760'
peer_review: peer-reviewed-journal
evidence_tier: B
design: Online US survey; mixed-modality stimuli (images, audio, video, audiovisual)
modality:
- image-face
- video
- audio
- audiovisual
stimuli: Mixed 2023-era generators
n_participants: 1276
n_note: preprint first posted March 2024 (arXiv 2403.16760)
topics:
- human-detection
- modality
summary: Mean detection was close to 50% chance; accuracy dropped for any synthetic content, foreign-language content, single-modality stimuli and synthetic images of faces; prior knowledge of synthetic media did not help; older participants did worse.
results:
- metric: Mean detection
  value: close to chance (50%)
  note: abstract gives no exact figure
  source_location: abstract
- metric: Lower accuracy when
  value: stimulus contains synthetic content, foreign language, single modality, or a synthetic human face
  note: ''
  source_location: abstract
- metric: Mixed-authenticity audiovisual
  value: harder
  note: ''
  source_location: abstract
- metric: Prior knowledge of synthetic media
  value: no significant effect
  note: ''
  source_location: abstract
- metric: Age
  value: older participants performed worse
  note: ''
  source_location: abstract
moderators: []
limitations:
- US sample only
verification:
  status: verified-abstract
  confidence: high
  checked: 2026-10-07
  via: arXiv 2403.16760 abstract page (journal ref CACM 68, 2025)
pmid: null
pmcid: null
openalex_id: null
oa_url: null
cited_in:
- MR-0001
- MR-0003
updated: '2026-10-07'
---

# As good as a coin toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli

> **Source record** `cooke-2024-coin-toss` · 2025 · Communications of the ACM  
> **Evidence tier:** B (peer-reviewed-journal) · **Verification:** verified-abstract (compiler confidence: high)  
> **Bottom line:** Mean detection was close to 50% chance; accuracy dropped for any synthetic content, foreign-language content, single-modality stimuli and synthetic images of faces; prior knowledge of synthetic media did not help; older participants did worse.

## Citation {#citation}

Di Cooke, Abigail Edwards, Sophia Barkoff, Kathryn Kelly (2025). As good as a coin toss: Human detection of AI-generated images, videos, audio, and audiovisual stimuli. *Communications of the ACM*, 68, 100-109. https://doi.org/10.1145/3729417

Verification entry (identifiers, resolvers, claims with source locations): [/data/citations.json#cooke-2024-coin-toss](/data/citations.json#cooke-2024-coin-toss)

## Study design {#design}

| Field | Value |
|---|---|
| Design | Online US survey; mixed-modality stimuli (images, audio, video, audiovisual) |
| Modality | image-face, video, audio, audiovisual |
| Stimuli | Mixed 2023-era generators |
| Participants (N) | 1276 |
| N detail | preprint first posted March 2024 (arXiv 2403.16760) |
| Topics | human-detection, modality |

## Results {#results}

| Metric | Value | Note |
|---|---|---|
| Mean detection | close to chance (50%) | abstract gives no exact figure |
| Lower accuracy when | stimulus contains synthetic content, foreign language, single modality, or a synthetic human face |  |
| Mixed-authenticity audiovisual | harder |  |
| Prior knowledge of synthetic media | no significant effect |  |
| Age | older participants performed worse |  |

## Limitations {#limitations}

- US sample only

## Cited in {#cited-in}

- [MR-0001](/metareports/human-detection-accuracy.md): Human Detection of Deepfakes: Accuracy, Bias, Confidence, and Training
- [MR-0003](/metareports/voice-cloning-human-detection.md): Voice Clones and Synthetic Speech: How Well Do People Detect Them?

## Verification {#verification}

| Field | Value |
|---|---|
| Status | `verified-abstract` |
| Compiler confidence | high |
| Checked on | 2026-10-07 |
| Via | arXiv 2403.16760 abstract page (journal ref CACM 68, 2025) |

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