AI Headshot Detector
Generated headshots are now standard equipment for fake recruiters, fake candidates and fake company pages — they cost nothing and look professional. Portraits happen to be the case where detection works best.
Why portraits are the easiest case
Face generators are trained on tightly aligned datasets, and that alignment leaves a signature no amount of polish removes.
Fixed facial geometry
Generated faces place eyes at near-identical coordinates across images. Line up several photos of the same 'person' and the alignment gives it away.
Studio background from nowhere
A clean gradient or blurred office that corresponds to no real room. Real headshots have a real place behind them.
Ears and jewellery
Mismatched ear shapes, an earring on one side only. Ears are as individual as fingerprints and generators handle them poorly.
Skin without pores
Retouching smooths skin; generation never had texture to begin with. Our texture and noise analyzers measure the difference.
Collars, glasses, lanyards
Frames that don't align across the bridge, a collar that changes weave, a lanyard that vanishes behind a shoulder and reappears wrong.
No photographer's metadata
A professional headshot carries camera, lens and often the studio's software trail. Generated files carry none.
How the analysis works
Upload the original file
Full resolution, straight from the source. Screenshots and re-saved copies destroy most of the evidence we measure.
12 independent methods run in parallel
Three neural networks look at the image as a whole. Nine forensic methods examine it as a signal: frequency (FFT) analysis, noise pattern, pixel-level statistics, EXIF metadata, Error Level Analysis, texture coherence, colour distribution, Benford's Law and edge detection.
You see the breakdown, not just a number
Every method reports separately, so you can tell whether the verdict rests on one weak signal or on nine that agree.
For any image that is not a portrait, Start with our AI image detector — it covers any image type and runs the same twelve methods.
How much each method counts
Most detectors give you one number from one model. We run twelve independent analyzers and weight them — three neural networks carry the majority, but nine forensic methods examine the file as a signal and can overrule them. Here is the exact weighting we use in production:
| Method | Weight in final score |
|---|---|
| Neural network #2 | 25% |
| Neural network #1 | 15% |
| Neural network #3 | 15% |
| EXIF metadata | 10% |
| Frequency (FFT) | 6% |
| Benford's Law | 6% |
| Noise pattern | 5% |
| Error Level Analysis | 4% |
| Texture coherence | 4% |
| Edge detection | 4% |
| Pixel statistics | 3% |
| Colour distribution | 3% |
What people actually upload
These are our own numbers, not an industry estimate — every check run through FakeSec since launch. The split is closer than most people expect: roughly four in ten uploads really do turn out to be generated.
Who uses this
- Recruiters — Candidates whose photo and CV do not add up.
- Jobseekers — Verifying that a recruiter and their company are real.
- Sales teams — Prospect profiles that look manufactured.
- Security teams — Impersonation of staff on social platforms.
Accuracy — and where it breaks down
On our internal benchmark of 240,000 images (120,000 AI-generated, 120,000 real) the combined score reaches up to 98% on unedited, full-resolution files. That number drops, sometimes sharply, in four situations — and you should know them before trusting any result:
- Heavy compression. Social platforms re-encode everything. A photo pulled from Instagram has already lost much of its noise signature.
- Screenshots. A screenshot is a new image of an image. Original metadata and compression history are gone.
- Stylised content. Flat colour and clean lines remove the texture and noise evidence forensic methods depend on.
- Post-processing. Added grain, filters, upscaling and manual retouching all mask generation traces.
No detector on the market is 100% accurate — ours included. Treat a high score as strong evidence, not as proof. When a decision matters, look at which of the 12 methods agreed.
Portraits are our strongest category — face generators leave systematic traces. The usual caveat still holds: a LinkedIn download is already re-compressed, so an original file gives a much firmer answer.
Frequently asked questions
Related tools
Check your first image now
Create a free account and get 3 checks. Full breakdown across all 12 methods, no card required.