I can't see it but I can Fine-tune it: On Encrypted Fine-tuning of Transformers using Fully Homomorphic Encryption
This addresses privacy concerns in machine learning for domains with sensitive data, though it is incremental as it builds on existing FHE methods for a specific task.
The paper tackles the problem of fine-tuning transformer models on encrypted data to preserve privacy, introducing BlindTuner which achieves comparable accuracy to non-encrypted models and shows speed improvements of 1.5x to 600x over prior work.
In today's machine learning landscape, fine-tuning pretrained transformer models has emerged as an essential technique, particularly in scenarios where access to task-aligned training data is limited. However, challenges surface when data sharing encounters obstacles due to stringent privacy regulations or user apprehension regarding personal information disclosure. Earlier works based on secure multiparty computation (SMC) and fully homomorphic encryption (FHE) for privacy-preserving machine learning (PPML) focused more on privacy-preserving inference than privacy-preserving training. In response, we introduce BlindTuner, a privacy-preserving fine-tuning system that enables transformer training exclusively on homomorphically encrypted data for image classification. Our extensive experimentation validates BlindTuner's effectiveness by demonstrating comparable accuracy to non-encrypted models. Notably, our findings highlight a substantial speed enhancement of 1.5x to 600x over previous work in this domain.