NovaFabric: Tamper-Evident, Replayable Evidence for Autonomous AI Agent Runs
NovaFabric seals autonomous AI agent runs into tamper-evident, replayable Run Capsules enabling third-party audit under EU AI Act and ISO 42001.
NovaFabric records autonomous agent runs without modifying agent logic into portable Run Capsules (fifteen-entity schema) sealed with DSSE signatures, RFC 3161 timestamps, a Merkle log, and redaction attestations, supporting four-mode replay and third-party Evidence Bundle verification. Evaluation shows tampering rejected across three tested classes, 14/14 credential types redacted while preserving 9/9 decoys, and 140/140 mutations localized; blast-radius queries reach 45.5ms p99 over 10M edges. Limits include only 2/10 tool-using workloads completing replay due to missing tool-response substitution and ingest capped at 61.6 req/s. The contribution integrates OpenTelemetry, DSSE/in-toto, and W3C PROV rather than new cryptography.
- Run Capsules sealed with DSSE, RFC 3161 timestamps, Merkle log, redaction attestation
- Tampering rejected across three classes; 14/14 credential types redacted with decoys preserved
- Replay gap: only 2/10 tool-using workloads complete due to tool-response substitution
- Targets EU AI Act, ISO 42001, NIST AI RMF audit needs; verification conditional on stated TCB
From the original article
1 min read at arxiv.orgWhen an autonomous AI agent does something consequential, what can be proven about what it did? Agent-observability platforms capture traces, but a trace is mutable: alterable undetected, with no recipe for re-executing it, silent on whether captured secrets were removed. Regulation (EU AI Act, ISO 42001, NIST AI RMF) presumes records an independent party can check.
By Mohsen Seyedkazemi Ardebili · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.