ZONN.ai Forensic Report

Case · 2B4FA6BE · IMAGE

Analyzed byAnonymous
ZONN Analysis
0

Probably real

More signals lean toward real than AI, but some give weaker readings. Worth a second look on close inspection.

Signal ConfidenceLimited · 47/100

Analysed Specimen

Original analysed image
Forensic suspicion heatmap
OriginalHeatmap
POS55/100
No flagged regions

Heads up — 3 things to know

Why this analysis might be off

We highlight every disagreement and unusual signal we found so you can judge for yourself. Stronger warnings come first; informational notes are at the bottom.

AI generator fingerprints detected

AI evidence

Frequency analysis (FFT score 81/100) shows modern diffusion-style upsampling patterns, but the ML models say "real". This combination is a known blind spot for newer generators (SDXL, FLUX, Midjourney v6) — the verdict above may be misleading.

Image is very small

Note

Dimensions 140×140 (under 256×256). Detection models cannot give a reliable answer on inputs this small.

Upsampling artifacts in the frequency domain

AI evidence

FFT analysis found strong upsampling patterns — a fingerprint of diffusion-model VAE decoders (latent → pixel-space upscale).

Origin Check

Trace this image elsewhere

Cross-reference the source against major reverse-image services. Each link opens in a new tab with the image URL preloaded — ZONN.ai does not re-upload the image.

Why this verdict

  • CommFor (4803 Generators)read real · 0/100

    CommFor detector trained across 4,803 generator variants for broad coverage.

  • Noise Patternflagged AI · 99/100

    Sensor-noise (PRNU) fingerprint check. Real cameras leave camera-unique noise.

Model Agreement

52%

Variance across 6 ML detectors. Higher agreement means the models converged on the same reading; lower agreement means treat the verdict with care.

Evidence — 16 detectors reviewed

What each detector saw

Each detector independently gave this imagea score from 0 (definitely real) to 100 (definitely AI). The score above is their weighted consensus — detectors with higher confidence count more. No single detector decides; you read the spread.

ML Models6 detectors · mean 28
▸ expand
CommFor (4803 Generators)
0
xRayon ConvNeXtV2
3
Bombek1 SigLIP+DINOv2
11
SigLIP AI Detector
63
INA v2 (FLUX/MJ)
38
Manipulation Map (IML-ViT)
50
Pixel & Frequency Forensics7 detectors · mean 58
▸ expand
Noise Pattern
99
Frequency Analysis
81
Color Distribution
25
Edge Consistency
75
Error Level Analysis
32
Pixel Analysis
45
Compression Quality
50
Provenance & Metadata3 detectors · mean 54
▸ expand
ICC Profile
62
Metadata
50
C2PA Provenance
50

Image Quality

Dimensions
140 × 140 px
Aspect
1.000
File size
1.8 KB
Bytes / pixel
0.094

Frequency Analysis

Radial1.000
DCT0.933
Upsampling1.000
Cross-channel0.310
Power-law β
-4.73
Grid energy
0.101

Edge Consistency

CV 0.153
Cell 1: 0.9825Cell 2: 1.1396Cell 3: 1.3093Cell 4: 1.0561Cell 5: 1.1442Cell 6: 1.4066Cell 7: 1.2797Cell 8: 1.3195Cell 9: 1.4021Cell 10: 0.9215Cell 11: 0.9900Cell 12: 1.2758Cell 13: 1.0968Cell 14: 0.8765Cell 15: 1.0625Cell 16: 0.8855

Per-region edge density (4 × 4 grid). Uneven distribution may indicate localized editing or splicing; uniform fields are typical of fully synthetic outputs.

Range: 0.87651.4066

Noise Fingerprint

Variance
0.78
Std deviation
0.88
Mean
-0.0
Spatial corr.
0.181
Mean Δ
0.72
σ
0.74
CV
1.025
Uniformity
-0.025

Provenance

Source Dossier

PlatformDirect upload
Author
Content Typeimage
Analyzed OnMay 14, 2026, 10:41 AM
Analyzed byAnonymous