What the detector examines
Lighting consistency, texture and noise patterns, compression artifacts, facial details, object boundaries, and other forensic indicators that may reveal synthetic or edited content.
DetectFake
Authenticity Engine
Upload a photo or video. DetectFake runs forensic-grade visual analysis and returns a verdict, confidence score, and the signals it relied on.
Guides: AI image detector · AI video detector · deepfake detection · how to tell if an image is AI · methodology and limitations
DetectFake checks photos, screenshots, artwork, and sampled video frames for patterns linked to generative AI, deepfakes, face swaps, and digital manipulation. Each scan returns a probabilistic verdict, confidence score, and the visual signals that influenced it, helping journalists, researchers, moderators, and everyday users review suspicious media faster.
Lighting consistency, texture and noise patterns, compression artifacts, facial details, object boundaries, and other forensic indicators that may reveal synthetic or edited content.
For video, DetectFake samples frames locally and compares evidence across the clip. Read the full guide to our AI video detector.
Start with three free daily scans or compare higher-volume options on the DetectFake pricing page.
DetectFake provides probabilistic forensic assessments and is not a substitute for expert review. Results should be interpreted alongside provenance data (C2PA, EXIF, chain of custody) before high-stakes decisions.