Finding copies across the web.
ShieldHer has distributed collection and indexing infrastructure. It explores accessible sources and prepares the media representations needed for copy retrieval.
Searching accessible sources
Redistribution can appear on pages with no connection to your account name or production title. Collection helps discover these assets without relying solely on name-based searches.
Indexed representations can then be compared with your references. Publishing context helps locate a copy: the page and source where the asset was found.
Understand copy recognitionFingerprints, representations and publishing context
The scale of the index
The index holds digital representations of more than 150 million unique images. This corpus broadens the collection available for copy searches; indexing throughput allows it to grow as new assets are collected.
- Unique images indexed
- More than 150 million unique images
- Indexing throughput
- More than 100,000 images per hour
Infrastructure figures · October 2026
These figures describe the unique images represented and the indexing throughput reported by ShieldHer. They do not measure recognition accuracy or coverage of the entire web.
Fingerprints (hashes) and representations enable comparison without retaining the image and video files in the index.
Data retention and privacyYour monitoring scope
We define the scope with you: assets to protect, catalogue references, priority sources and search frequency. Monitoring arrangements are specified within the closed beta.
The web also includes private spaces, restricted access and content unavailable to crawlers. Coverage concerns a defined scope that evolves with sources and applications.
Discuss your scope