Frequently Asked Questions

Every photo taken by a real camera passes through five physical stages. Each stage leaves traces in the pixels that are impossible to fake. Our 30+ signals measure each stage independently.

AI skips all five. Edits break one or more. Recaptures add their own.

Every image is scored by five independent detectors:

Each detector weighs the signals that matter most for that specific image and shows exactly which signals influenced its answer.

AI image generators (ChatGPT, Midjourney, Stable Diffusion, DALL-E) synthesize pixels directly from neural networks. They skip the entire camera pipeline. No sensor noise, no Bayer pattern, no PRNU fingerprint, no hardware JPEG encoder.

Our 30+ physics signals measure what should be there from a real camera. When it's missing, we know. This is fundamentally different from AI detectors that try to recognize "what AI looks like," which breaks every time a new generator comes out.

Most AI detectors use neural networks trained to recognize what AI output "looks like." They break every time a new generator launches. Proof measures the physics fingerprint the camera pipeline leaves in every pixel. Real cameras produce signals that cannot be faked regardless of what AI tool was used.

Every result includes per-image signal contributions showing exactly which signals drove the verdict. No black box.

JPEG, HEIC, PNG, and WebP. All formats are analyzed automatically. Non-JPEG files are normalized while preserving the original file forensics for analysis.

All uploaded images are automatically deleted after 24 hours. Your data is never sold or shared. If you need an image removed sooner, contact contactus@proofme.ai.