Spatio-Temporal Provenance Guard: Detecting Privilege Escalation Attacks That Exploit Spatio-Temporal Data Loss in Multi-Agent MCP Environments
Applied Sciences · 18.11.2026 · 16 (22) · 11449
DOI: 10.3390/app162211449 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 18.11.2026. Verfasst von Deuk-Hun Kim und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea.
Abstract (Originalsprache)
Multi-agent systems using the Model Context Protocol (MCP) can lose provenance across storage and session boundaries. This spatio-temporal data loss enables an adversary on the ingestion path to distribute an outbound-transfer directive across incomplete records for a privileged agent to assemble and execute. We propose Spatio-Temporal Provenance Guard (STPG), a gateway defense that persists connector provenance, regroups records by source lineage, and authorizes an external routing call only when a trusted directive is witnessed to target that destination and passes a deterministic structural check. Comparisons use evidence adapters on a common kernel, not published defenses. On a Google Cloud testbed with Gemini agents, STPG blocked all 648 attacks and passed 69 of 71 approved transfers. It matched all specified decisions on a policy challenge set and 190/260 on a frozen set from a second model family. Requiring two witness models to agree reduced false authorizations on descriptive notices from 53 to 25 of 150. On a second held-out set generated after all settings were frozen, conformance was 215/260, rising to 229/260 with witness agreement and an extended resolver. Limits remain in reference resolution, descriptive notices, and trusted rewrites, so the results support bounded, destination-level enforcement on synthetic data.
Förderung
- National Research Foundation of Korea
Zitieren
APA
Kim, D., & Kwak, J. (2026). Spatio-Temporal Provenance Guard: Detecting Privilege Escalation Attacks That Exploit Spatio-Temporal Data Loss in Multi-Agent MCP Environments. Applied Sciences, 16(22), 11449. https://doi.org/10.3390/app162211449
Vancouver
Kim D, Kwak J. Spatio-Temporal Provenance Guard: Detecting Privilege Escalation Attacks That Exploit Spatio-Temporal Data Loss in Multi-Agent MCP Environments. Applied Sciences. 2026;16(22):11449. doi:10.3390/app162211449
BibTeX
@article{Kim2026,
author = {Kim, Deuk-Hun and Kwak, Jin},
title = {Spatio-Temporal Provenance Guard: Detecting Privilege Escalation Attacks That Exploit Spatio-Temporal Data Loss in Multi-Agent MCP Environments},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {22},
pages = {11449},
doi = {10.3390/app162211449}
}
EUVIMED