Metraipolis › archive › dc_dc0b4cda7d23
Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems — arXiv:2608.30387
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30387
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:25:52.438Z
- SHA-256 of the archived text
7d5bdd6e799747d5de4efee33c6f8bcdaf6067b0244509211e97fccdb4f212c0- Stable URL of this page
https://metraipolis.com/documento/dc_dc0b4cda7d23
How to cite
Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems — arXiv:2608.30387 — arXiv (en), https://arxiv.org/abs/2608.30387 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dc0b4cda7d23 (Metraipolis archive dc_dc0b4cda7d23, sha256 7d5bdd6e799747d5de4efee33c6f8bcdaf6067b0244509211e97fccdb4f212c0)
BibTeX
@misc{dcdc0b4cda7d23,
title = {Attesting Outputs and Delegation Ancestry in Multi-Agent AI Systems — arXiv:2608.30387},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30387},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dc0b4cda7d23; sha256 7d5bdd6e799747d5de4efee33c6f8bcdaf6067b0244509211e97fccdb4f212c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30387. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent applications delegate work across independently operated deployers. After an incident, a verifier must answer two questions: which deployer released the reported bytes, and whether each cross-deployer edge was authorized. Credentials establish who may act, but need not bind them to later output bytes or prove both deployers authorized a dynamically created edge. We present a two-layer attestation design for dynamic delegation without a shared authority, public log, or precommitted workflow. A trusted deployer runtime signs a hash of each released output; this records released bytes but does not prevent prompt injection. Ancestry evidence records edge authorization. Under a unified threat model, we compare a signed linked list, a Merkle-chain variant, and a co-signed DAG. The primitives are standard; the contribution is deployer-side binding and the evidence needed for the two questions. After child-key compromise, the single-signer designs permit an unauthorized parent binding, whereas the co-signed DAG rejects it because the parent must authorize the edge. Fixed adversary matrices and regression tests validate the composed verifier. On an Apple M1 Pro, ancestry-only checks take 24.3-499.2us per hop. In a live local multi-service workflow, a parent discovers the child's A2A Agent Card; the child calls an MCP tool and releases local-LLM output: all 30 signed-DAG tasks passed complete verification, while a controlled child-key-only claim was rejected; its mean end-to-end latency was 813.1ms versus 770.8ms without evidence. In a complementary three-availability-zone AWS deployment, all 1,000 valid co-signed-DAG paths verified; issuance averaged 3.651ms and complete verification 5.015ms. The cloud result excludes TLS/mTLS, KMS, and model-serving latency. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2608.30387 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T08:10:59.890Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).