Category
Research
4 articles in this category.
The AI Detector Landscape in 2026 — Who Detects What, and How Well
The detector market in 2026 looks nothing like the detector market in 2023. Three years ago, "AI detection" meant a single confidence score from a single model. Today it means a fragmented ecosystem…
Why AI Video Detectors Are Failing in 2026 — A Forensic Breakdown
In 2024, AI video detectors worked well enough to be useful. A trained classifier could spot Sora 1 and Runway Gen 2 output with around 90% accuracy on standard benchmarks, and the public tools — Hiv…
C2PA & Content Credentials Explained — The New Provenance Standard
Content Credentials are the most consequential thing to happen to image authenticity since EXIF, and one of the most widely misunderstood standards on the open web. The press coverage tends to oscill…
PRNU, FFT & Sensor Noise — The Forensics Behind Image Authenticity
Image forensics is a small, mathematically dense field that quietly underpins everything from courtroom exhibits to AI detection startups. Three pillars do most of the heavy lifting: PRNU (the sensor…