← Search

Dongjin Park

1 accepted papers

2025

Powerformer: Efficient and High-Accuracy Privacy-Preserving Language Model with Homomorphic Encryption

ACL 2025long

We propose Powerformer, an efficient homomorphic encryption (HE)-based privacy-preserving language model (PPLM) designed to reduce computation overhead while maintaining model performance. Powerformer incorporates three key techniques to optimize encrypted computations:1. A novel distillation techni…