Skip to content

Integration: Cryptographic signing for evaluation reports with asqav #1846

@jagmarques

Description

@jagmarques

Evidently generates evaluation reports and monitoring data for ML/LLM systems. Proposing an asqav integration that cryptographically signs these outputs.

Value: When you run an evaluation or monitoring check, the results get signed with ML-DSA-65 (quantum-safe, NIST FIPS 204). This creates verifiable proof that a specific evaluation happened, with specific results, at a specific time - exactly what auditors need for EU AI Act, SOC2, and HIPAA compliance.

Implementation: Could work as a post-evaluation hook that signs report snapshots before storage.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions