LATIDIA · Ciberseguridad

ROSETTA: decodificación LLM eficiente y precisa para preservar la privacidad a través de la evaluación híbrida CKKS/TFHE

arXiv: 2609.16915v1Tipo de anuncio: nuevo Resumen: Los modelos generativos de lenguaje grande (LLM) han logrado un rendimiento de vanguardia en muchas tareas del mundo real, como la generación de código y la respuesta a preguntas. Estos modelos pre

La noticia

arXiv:2609.16915v1 Announce Type: new Abstract: Generative large language models (LLMs) have achieved state-of-the-art performance on many real-world tasks such as code generation and question answering. These models predominantly rely on an autoregressive decoding strategy that generates output tokens sequentially. However, their pervasive deployment raises serious privacy concerns, motivating private inference frameworks based on fully homomorphic encryption (FHE). A major limitation of existing FHE frameworks is their inefficiency in evaluating nonlinear operations, which incur substantial overhead and dominate the decode stage. In this paper, we propose ROSETTA, a hybrid CKKS/TFHE framework that overcomes this limitation. We first observe that nonlinear operations in the decode stage exhibit heterogeneous workload patterns, which can