Metraipolis › archive › dc_89bde1282e2f

Agentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money — arXiv:2609.35886

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35886
License (as archived)
CC0-1.0
Archived
2026-10-07T16:24:55.294Z
SHA-256 of the archived text
72aec1db9cfa44bebbbc8459aee2771a6689c7e414fbe158539cce5a217203a3
Stable URL of this page
https://metraipolis.com/documento/dc_89bde1282e2f

How to cite

Agentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money — arXiv:2609.35886 — arXiv (en), https://arxiv.org/abs/2609.35886 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89bde1282e2f (Metraipolis archive dc_89bde1282e2f, sha256 72aec1db9cfa44bebbbc8459aee2771a6689c7e414fbe158539cce5a217203a3)
BibTeX
@misc{dc89bde1282e2f,
  title = {Agentic Commerce Bench: Measuring Fraud Detection for Agents That Spend Money — arXiv:2609.35886},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35886},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89bde1282e2f; sha256 72aec1db9cfa44bebbbc8459aee2771a6689c7e414fbe158539cce5a217203a3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35886. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a counterparty with the correct domain, the correct settlement address and a genuinely delivered service can charge more than it should, and no check keyed on identity will see it. We present three artefacts for measuring and reducing that loss. First, a taxonomy of agentic commerce fraud that separates five observation levels (agent reasoning, wire, settlement rail, counterparty, principal) from the request-level and history-level evidence available at each, and records which levels can observe which attacks. Second, Agentic Commerce Bench (ACB), a benchmark of twenty fraud classes generated from production aggregates, 1,647 catalogued service operations and 1,068 settlements, of which six involve a counterparty that is exactly who it claims to be. Third, gordonguard, an open-source detector stack and offline harness with which an operator can audit an agent configuration, replay hostile counterparties without an account, and run the same detectors inline. Calibrating to a stated false-positive budget on clean training traffic gives a 6.5% clean flag rate, replicated across three independent generations, and leaves eight of twenty classes no better than chance. On the four classes a reasoning layer can observe, a widely used agent security scanner run over its jailbreak-detection panel scores zero on all four, while correctly scoring 1.0 on a jailbreak supplied as a control. A measured median payment of $0.007 places a hard constraint on deployment: one human review costs 143 times the value of the payment it examines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.35886 — 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 2026-10-07T15:54:53.731Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).