LATIDIA · Ciberseguridad

Comprender los límites de seguridad de la protección LLM en el dispositivo basada en ofuscación

arXiv:2609.10117v2 Tipo de Anuncio: reemplazar Resumen: Los Entornos de Ejecución Confiable (Tee) ofrecen un mecanismo prometedor para salvaguardar la propiedad intelectual de los Modelos de Lenguaje Grande (LLM) en el dispositivo. Para superar el

La noticia

arXiv:2609.10117v2 Announce Type: replace Abstract: Trusted Execution Environments (TEEs) offer a promising mechanism for safeguarding the intellectual property of on-device Large Language Models (LLMs). To overcome the inherent computational bottlenecks of TEEs, existing TEE-Shielded LLM Partition (TSLP) methods apply efficient obfuscation schemes to computationally intensive layers, offloading them to external GPUs while retaining only lightweight operations within the TEE. Although a growing body of TSLP-based approaches has emerged, these defense mechanisms remain largely heuristic. Consequently, some methods are proven vulnerable to certain specialized adversarial attacks designed to exploit their specific architectural implementations. To overcome the limitations of these heuristic designs, this paper addresses a fundamental research question: can we establish