Metraipolis › archive › dc_fe93c552d135

DGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards — arXiv:2609.34913

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34913
License (as archived)
CC0-1.0
Archived
2026-10-07T20:58:19.404Z
SHA-256 of the archived text
171cf50ae3fa66be6e783664c718df9073dc33823fd8baf505027ad2f9b079b7
Stable URL of this page
https://metraipolis.com/documento/dc_fe93c552d135

How to cite

DGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards — arXiv:2609.34913 — arXiv (en), https://arxiv.org/abs/2609.34913 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe93c552d135 (Metraipolis archive dc_fe93c552d135, sha256 171cf50ae3fa66be6e783664c718df9073dc33823fd8baf505027ad2f9b079b7)
BibTeX
@misc{dcfe93c552d135,
  title = {DGF-Bench: A Benchmark for Simulating and Auditing Deception Against Multi-Agent Governance Boards — arXiv:2609.34913},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34913},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe93c552d135; sha256 171cf50ae3fa66be6e783664c718df9073dc33823fd8baf505027ad2f9b079b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34913. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool-using language-model agents can review enterprise projects as governance boards do: they read the evidence, apply written rules and decide whether the project may proceed. Part of that evidence comes from suppliers and project members with a stake in the decision. DGF-Bench is a benchmark in which a board of agents (specialist gates and a General gate that consolidates their decisions) reviews synthetic dossiers while an attacker plants deceptive content in evidence the organization does not vouch for. Dossiers are generated from canonical facts under 61 executable rules, with 42 authoritative records and 32 narrative documents; every gate is certified decidable from those records. Attacks never change an authoritative value, so an attacked dossier keeps the reference decisions of its clean copy. A success is attributable only when the agent receives the injection and takes the exact injected action, which it does not take on the paired clean dossier; the DGF score is the share of applicable fixed attacks a model blocks. Reading documents and records themselves, five of six models were outcome-strict (disposition, findings, actions and authorization all correct) on 82 to 85 of 85 gates. Over 2,622 attacked gate runs, seven direct-order, false-data and false-authority attacks obtained one attributable success against these five, whereas task-aligned attacks imitating the organization's own process passed against four of them: a record note citing a fake review procedure lowered GPT-6 Luna Pro from 34 to 6 outcome-strict gates and DeepSeek V4 Pro from 33 to 7. DGF scores ranged from 96.2 to 26.9, and a policy-aware adaptive attacker writing in records succeeded against five of six models. The approval tool executed no forged approval, yet deceived agents submitted approvals that the rules forbid. The open-source package dgf-bench computes the DGF score with one command.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.34913 — 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 2026-10-07T20:29:01.714Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).