HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption

2024-03-21 · Seewoo Lee, Garam Lee, Jung Woo Kim, Junbum Shin, Mun-Kyu Lee

Transfer learning is a de facto standard method for efficiently training machine learning models for data-scarce problems by adding and fine-tuning new classification layers to a model pre-trained on large datasets. Although numerous previous studies proposed to use homomorphic encryption to resolve the data privacy issue in transfer learning in the machine learning as a service setting, most of them only focused on encrypted inference. In this study, we present HETAL, an efficient Homomorphic Encryption based Transfer Learning algorithm, that protects the client's privacy in training tasks by encrypting the client data using the CKKS homomorphic encryption scheme. HETAL is the first practical scheme that strictly provides encrypted training, adopting validation-based early stopping and achieving the accuracy of nonencrypted training. We propose an efficient encrypted matrix multiplication algorithm, which is 1.8 to 323 times faster than prior methods, and a highly precise softmax approximation algorithm with increased coverage. The experimental results for five well-known benchmark datasets show total training times of 567-3442 seconds, which is less than an hour.

📄 PDF Abstract BibTeX arXiv:2403.14111

Code (1)

cryptolabinc/hetal 공식 구현 pytorch

Tasks

Privacy PreservingTransfer Learning

Methods 이 논문이 사용한 방법론

Golden Queue Managers 설명 없음

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption

2017-04-07 · ICCV 2017 10 · Ryo Yonetani, Vishnu Naresh Boddeti, Kris M. Kitani, Yoichi Sato

We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and …

Privacy Preserving

Privacy-Preserving 3-Layer Neural Network Training

2023-08-18 · John Chiang

In this manuscript, we consider the problem of privacy-preserving training of neural networks in the mere homomorphic encryption setting. We combine several exsiting techniques available, extend some of them, and finally…

Privacy Preserving regression

FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learning

2020-07-21 · Zhaoxiong Yang, Shuihai Hu, Kai Chen

With the increasing awareness of privacy protection and data fragmentation problem, federated learning has been emerging as a new paradigm of machine learning. Federated learning tends to utilize various privacy preservi…

Federated Learning High-Level Synthesis Privacy Preserving

MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption

2024-01-17 · Prajwal Panzade, Daniel Takabi, Zhipeng Cai

Advancements in machine learning (ML) have significantly revolutionized medical image analysis, prompting hospitals to rely on external ML services. However, the exchange of sensitive patient data, such as chest X-rays, …

Medical Image Analysis Privacy Preserving

A Privacy-Centric Approach: Scalable and Secure Federated Learning Enabled by Hybrid Homomorphic Encryption

2025-07-20 · Khoa Nguyen, Tanveer Khan, Hossein Abdinasibfar, Antonis Michalas arxiv

Federated Learning (FL) enables collaborative model training without sharing raw data, making it a promising approach for privacy-sensitive domains. Despite its potential, FL faces significant challenges, particularly in…

Federated Learning