Pacifo speeds up encrypted ResNet inference for private AI services
Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service
Cryptography and SecurityArtificial Intelligence
Summary
Machine learning services often need your data to work, raising privacy worries. The authors present Pacifo, a method that lets these services run a popular image recognition model called ResNet on encrypted data, so your private info stays hidden. Pacifo makes this process much faster and keeps accuracy high by cleverly reducing heavy encryption steps. This could help companies offer AI services that respect user privacy without slowing down.
What this means in practice
- •For cloud service providers: Offer machine learning inference on fully encrypted user data efficiently with reduced computation time and preserved model accuracy.$Commercial implications: Enables privacy-preserving AI inference services that maintain performance, appealing to clients needing confidential data processing.
- •For enterprise it security teams: Deploy faster privacy-preserving AI models for sensitive data analysis without exposing raw client data to servers.
Authors
Yang Li, Gang He, Ruichen Zhang, Guangyuan Liu, Yinqiu Liu
Abstract
Machine Learning as a Service (MLaaS) has become a popular paradigm for deploying AI applications. However, it raises significant privacy concerns that the raw client data needs to be uploaded to the server for inference services. Private inference using Fully Homomorphic Encryption (FHE) offers a solution by allowing computations directly on encrypted data, with only the final results decrypted on a client side. However, current practical implementations still suffer from large computational overhead and high latency due to the cost of FHE operations. In this paper, we propose Pacifo, a framework that adapts customized fine-tuning strategies to efficiently evaluate the ResNet20 model in the context of FHE. Specifically, Pacifo introduces a public-private layer partitioning scheme and an efficient ReLU approximation, significantly reducing the number of private layers and costly FHE operations during inference. It also offers flexible security configurations to accommodate varying client privacy requirements. Compared to state-of-the-art FHE implementations of ResNet20, Pacifo achieves a speedup of $3.7-21.7\times$ in runtime while effectively preserving $95\%-99\%$ of the original plaintext model accuracy across downstream tasks. Pacifo is open-sourced at https://github.com/BryceYangLi/Pacifo.