Ditto: Quantization-aware Secure Inference of Transformers upon MPC

arXiv:2405.05525v1 Announce Type: cross
Abstract: Due to the rising privacy concerns on sensitive client data and trained models like Transformers, secure multi-party computation (MPC) techniques are employed to enable secure inference despite attendant overhead. Existing works attempt to reduce the overhead using more MPC-friendly non-linear function approximations. However, the integration of quantization widely used in plaintext inference into the MPC domain remains unclear. To bridge this gap, we propose the framework named Ditto to enable more efficient quantization-aware secure Transformer …

abstract arxiv client computation concerns cs.cr cs.lg data ditto function however inference integration linear mpc non-linear privacy quantization reduce transformers type