Real data in real pixels. Not metadata. Not headers. The pixels themselves.
Upload an image or paste a URL. DIAP extracts provenance data embedded directly in pixel values using LSB steganography. The authorization chain lives in the actual bits of the image.
Drop a file here or click to browse
Images (PNG, JPEG, WebP) • Videos (MP4, WebM, MOV) • Audio (MP3, WAV, OGG) — up to 200MB
How pixel watermark verification works
Upload an image
Any PNG, JPEG, or WebP — downloaded from a dashboard, screenshot, from social media, or fetched from a URL.
Pixel-level extraction
DIAP reads the least significant bits (LSB) of every pixel in the image. If steganographic data is found, the payload is decoded. If compression destroyed the LSB data, perceptual hash matching is used as fallback.
Full provenance chain
The extracted payload reveals: talent identity, authorizing studio, license status, render receipt ID, and HMAC-SHA256 signature verification.
LSB Steganography
PRIMARY VERIFICATION METHODThe full DIAP payload (protocol version, receipt ID, license token, talent ID, studio name, timestamp, asset ID) plus an HMAC-SHA256 signature is encoded into the least significant bits of RGB channels. Each pixel carries 3 bits. A 1920×1080 image can store over 770KB of hidden data.
Perceptual Hash Fallback
COMPRESSION-RESISTANT MATCHINGIf social media recompression or heavy JPEG compression destroys the LSB data, DIAP falls back to perceptual hash matching. A 64-bit visual fingerprint of the image is compared against all known watermarked assets. This survives resizing, format conversion, and moderate quality loss (Hamming distance threshold: 10/64 bits).
Try it yourself
Go to the Marvel Studios dashboard, download any watermarked asset, then upload it here. The provenance chain will be extracted directly from the pixel data — no database lookup, no metadata, no EXIF. The data is in the pixels themselves.