Metraipolis › archive › dc_5638121a8169
Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy — arXiv:2610.39532
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39532
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:13:18.220Z
- SHA-256 of the archived text
805750c3e43b9be8b30fec39de3dd5933b64ed4d158a875ba6d935bbdbdc640d- Stable URL of this page
https://metraipolis.com/documento/dc_5638121a8169
How to cite
Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy — arXiv:2610.39532 — arXiv (en), https://arxiv.org/abs/2610.39532 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5638121a8169 (Metraipolis archive dc_5638121a8169, sha256 805750c3e43b9be8b30fec39de3dd5933b64ed4d158a875ba6d935bbdbdc640d)
BibTeX
@misc{dc5638121a8169,
title = {Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy — arXiv:2610.39532},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39532},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5638121a8169; sha256 805750c3e43b9be8b30fec39de3dd5933b64ed4d158a875ba6d935bbdbdc640d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39532. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual interactions: a release appropriate in isolation may become inappropriate when combined with information previously disclosed to a recipient or propagated to downstream agents along the planned workflow. Existing Contextual Integrity (CI) mechanisms for agentic systems typically rely on local judgments that assess each disclosure in isolation, with or without regard to the recipient's history, but do not account for how information propagates downstream. However, compliance at the current boundary does not guarantee appropriateness across the workflow. We introduce Task-Graph Contextual Integrity (TG-CI), to our knowledge the first task-graph-native formalization of Contextual Integrity for multi-agent systems. TG-CI represents a workflow as a Multi-Agent Task Graph (MATG) and extends CI from atomic transfers to stateful, graph-level information flows by jointly considering an item's intended propagation scope and recipients' evolving disclosure states. We operationalize TG-CI through propagation-scoped authorization under two complementary policies: Full-Scope, which requires admissibility across the complete downstream scope, and Auto-Region, which confines each item to its maximal admissible region using lightweight frontier gates. We further introduce MAPLE-Bench, a benchmark of 144 cases across four scenarios that jointly vary MATG topology, disclosure history, compromised-agent placement, and item-level privacy policies. In our primary experimental configuration, TG-CI reduces the mean unauthorized disclosure count by 85.8-94.1% relative to the Local-History CI baseline, while retaining 93.6-96.1% of the baseline's task accuracy, with the two enforcement policies providing complementary privacy--cost--utility trade-offs. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.39532 — 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 2026-10-31T06:07:08.721Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).