LLM Exposure Monitoring: Platform Openness, Recording Depth, and the Case for an Open Standard

Fuente: Zenodo
Guardado en:
Detalles Bibliográficos
Autor principal: Alex, Li
Formato: Recurso digital
Lenguaje:inglés
Publicado: Zenodo 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866901640762621952
author Alex, Li
author_facet Alex, Li
contents <p>Prior work on AI agent accountability, notably the AEGIS framework, focused on recording agent actions. This paper addresses a complementary problem: recording agent exposure—what data AI agents access, ingest, and transmit across heterogeneous platforms. We formalize the LLM Exposure Surface (Read, Write, API, and Context Exposure), define an Exposure Threat Model (ET1–ET5) grounded in empirical incidents, and introduce a Platform Openness Taxonomy classifying platforms into three recording depth tiers based on webhook and API capabilities. We show that variation in recording depth is primarily a platform strategy issue, not a technical limitation. We propose Open Recording Patterns, a standardized exposure event schema extending AEGIS L1, and illustrate the framework through a dual-stream corroboration architecture that cross-references agent-reported events against platform-verified events. Classification of 13 platforms reveals that only 4 (31%) currently support full real-time exposure monitoring.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19112061
institution Zenodo
language eng
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle LLM Exposure Monitoring: Platform Openness, Recording Depth, and the Case for an Open Standard
Alex, Li
AI governance
LLM exposure
agent accountability
platform openness
recording depth
open standard
regulatory compliance
exposure monitoring
AEGIS
<p>Prior work on AI agent accountability, notably the AEGIS framework, focused on recording agent actions. This paper addresses a complementary problem: recording agent exposure—what data AI agents access, ingest, and transmit across heterogeneous platforms. We formalize the LLM Exposure Surface (Read, Write, API, and Context Exposure), define an Exposure Threat Model (ET1–ET5) grounded in empirical incidents, and introduce a Platform Openness Taxonomy classifying platforms into three recording depth tiers based on webhook and API capabilities. We show that variation in recording depth is primarily a platform strategy issue, not a technical limitation. We propose Open Recording Patterns, a standardized exposure event schema extending AEGIS L1, and illustrate the framework through a dual-stream corroboration architecture that cross-references agent-reported events against platform-verified events. Classification of 13 platforms reveals that only 4 (31%) currently support full real-time exposure monitoring.</p>
title LLM Exposure Monitoring: Platform Openness, Recording Depth, and the Case for an Open Standard
topic AI governance
LLM exposure
agent accountability
platform openness
recording depth
open standard
regulatory compliance
exposure monitoring
AEGIS
url https://doi.org/10.5281/zenodo.19112061