News Photo Checker
A photograph of something that never happened now spreads faster than the correction ever will. This is the check to run before you publish, share or believe it — and it takes less time than reading the caption.
How a fake news image usually fails
Fabricated news imagery divides into three types, and each leaves different evidence. Knowing which you are looking at decides what to do next.
Fully generated scene
An event that never took place. Detected by generation statistics: flat noise, even detail distribution, no capture parameters.
Real photo, altered
Something added or removed — a crowd enlarged, an object erased. Shows as a region with its own compression and noise history.
Real photo, false caption
The most common and the hardest: an authentic image from another place or year, recycled. Forensics finds nothing, because nothing is wrong with the file. Reverse image search is the tool for this one.
Impossible details
Text on signs and banners, uniform insignia, licence plates and reflections — generators still fail these at close inspection.
Metadata mismatch
A capture date that contradicts the claimed event, or software that names an editor. Usually stripped by the time it reaches you.
Crowd and shadow logic
Repeated faces in a crowd, shadows falling in different directions, reflections that do not correspond to the scene.
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 outside a news context, 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.
Verification order that works
- Run the forensic check — Rules out generation and local manipulation.
- Reverse image search — Catches the recycled-photo case forensics cannot.
- Check the metadata — If any survived, date and device are worth reading.
- Find the original source — Who posted it first, and where — the answer is usually there.
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.
Be clear about what a clean result means: the file was probably photographed and not altered. It says nothing about whether the caption is true. The most common form of visual misinformation is a genuine photo with a false story attached — no image tool can catch that.
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.