ARION: Attention-Optimized Transformer Inference on Encrypted Data↗ (원문, 새 창)

본문 미리보기

Privacy-preserving Transformer inference (PPTI) is essential for deploying large language models (LLMs) such as BERT and LLaMA in sensitive domains. In these models, the attention mechanism is both the main source of expressiveness and the dominant performance bottleneck under fully homomorphic encryption (FHE), due to large ciphertext matrix multiplications and the softmax nonlinearity. This paper presents Arion, a non-interactive FHE-based PPTI protocol that specifically optimizes the computat