Signed forensic reports with verifiable chain of custody

A detection result is only useful in a dispute, a court or a newsroom if others can trust it. sealverity.ai produces signed, versioned forensic reports and gives every recipient a public way to confirm a report is genuine and unaltered.

What a report contains

Each report records the evidence file's SHA-256 hash, the hash-chained chain of custody, the detectors used with their versions, the combined score and agreement band, localisation snapshots such as heatmaps and timelines, metadata and EXIF, the AI review, provenance findings and the analyst's decision with its reason.

Two templates are available: an investigation report and an expert witness statement. Before signing, the analyst types their name and re-confirms their password.

SHA-256 evidence hashes
Hash-chained, append-only chain of custody
Detector names and versions
Heatmap and timeline snapshots
Analyst decision with recorded reason

Ed25519 signatures and public verification

The finished PDF is hashed and signed with the organisation's Ed25519 key. Reports are immutable and versioned: a correction creates a new version instead of changing the old one. Each report includes a QR code that links to the public verification page, where anyone can upload the PDF or enter its ID to confirm the signature and that the file has not been altered.

C2PA content credentials

sealverity.ai reads C2PA content credentials at intake and takes provenance into account in its analysis. Organisations can also seal their own official media with content credentials; the public verify page then lets anyone check whether a file matches a sealed original or is an altered copy.

Tamper-evident by design

Every action, from upload to decision, is written to an append-only audit log that is hash-chained per organisation, so any attempt to edit history breaks the chain. Retention purges issue signed deletion certificates, and audit logs can be exported or streamed to a SIEM.

Who relies on it

Law enforcement and investigators preparing evidence, legal teams and expert witnesses, compliance teams documenting fraud decisions, and newsrooms that need to show how a verification was carried out.

Part of one investigation platform

This capability is part of sealverity.ai, a single platform for media authenticity and investigations. Findings from images, video, audio, live calls, identity checks and social and news monitoring can be linked to cases, entities and a link graph, with risk scores that show which factors contributed. Access is protected by mandatory multi-factor authentication, single sign-on and SCIM provisioning, five roles, retention policies and legal hold. Organisations can bring their own self-hosted detectors or switch on sovereign mode, which blocks every external call on the server and logs each blocked attempt. Integrations include a browser extension, Slack and Teams, email scanning, webhooks, SIEM connectors and a REST API.