Homomorphic Encryption

Homomorphic encryption (HE) allows computations on encrypted data without decryption, addressing privacy concerns in machine learning. Current research focuses on applying HE to enhance the privacy of large language models (LLMs) and federated learning (FL), often involving optimizations for specific model architectures like transformers and the development of novel algorithms to mitigate computational overhead and address vulnerabilities. This field is significant because it enables secure collaborative machine learning and the deployment of AI services that protect sensitive data, impacting various sectors including healthcare, finance, and personal data management.

Papers

August 18, 2023

Privacy-Preserving 3-Layer Neural Network Training
John Chiang
Neural Network Homomorphic Encryption Classification Problem Privacy Preserving Training

August 17, 2023

Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Service
Jaewoo Park, Chenghao Quan, Hyungon Moon, Jongeun Lee
High Efficiency Homomorphic Encryption Hyperdimensional Computing Search and Rescue Machine Learning a a Service

August 10, 2023

A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks
Farzad Nikfam, Raffaele Casaburi, Alberto Marchisio, Maurizio Martina, Muhammad Shafique
Deep Neural Network Spiking Neural Network Homomorphic Encryption

August 2, 2023

Integrating Homomorphic Encryption and Trusted Execution Technology for Autonomous and Confidential Model Refining in Cloud
Pinglan Liu, Wensheng Zhang
Homomorphic Encryption Cloud Computing Legal Autonomy Trusted Execution Environment Encrypted Model Model Confidentiality

July 25, 2023

Blockchain-based Optimized Client Selection and Privacy Preserved Framework for Federated Learning
Attia Qammar, Abdenacer Naouri, Jianguo Ding, Huansheng Ning
New Framework Privacy Preserving Privacy Policy Homomorphic Encryption Smart Contract Client Selection

July 20, 2023

SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning
Ziyao Ren, Yan Kang, Lixin Fan, Linghua Yang, Yongxin Tong, Qiang Yang
Privacy Preserving Homomorphic Encryption PRIvacy Leakage

July 9, 2023

Towards Fast and Scalable Private Inference
Jianqiao Mo, Karthik Garimella, Negar Neda, Austin Ebel, Brandon Reagen
Homomorphic Encryption Encryption Method Private Inference Privacy Preserving Computation Oblivious Transfer

June 26, 2023

Practical Privacy-Preserving Gaussian Process Regression via Secret Sharing
Jinglong Luo, Yehong Zhang, Jiaqi Zhang, Shuang Qin, Hui Wang, Yue Yu, Zenglin Xu
Differential Privacy Homomorphic Encryption Gaussian Process Regression Practical Application Secure Multi Party Computation Secret Sharing

June 19, 2023

ArctyrEX : Accelerated Encrypted Execution of General-Purpose Applications
Charles Gouert, Vinu Joseph, Steven Dalton, Cedric Augonnet, Michael Garland, Nektarios Georgios Tsoutsos
Financial Application Homomorphic Encryption Secure Computation Efficient Homomorphic Arbitrary Computation

June 15, 2023

June 11, 2023

Efficient Skip Connections Realization for Secure Inference on Encrypted Data
Nir Drucker, Itamar Zimerman
Homomorphic Encryption Deep Learning Application Skip Connection Secure Inference Cryptographic Building Block

June 8, 2023

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users
Yogachandran Rahulamathavan, Charuka Herath, Xiaolan Liu, Sangarapillai Lambotharan, Carsten Maple
Homomorphic Encryption PRIvacy Leakage Encryption Method

May 28, 2023

A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning
Xiaojin Zhang, Yan Kang, Lixin Fan, Kai Chen, Qiang Yang
Federated Learning Many Parameter Homomorphic Encryption PRIvacy Leakage Meta Learning Framework Secret Sharing Protection Mechanism

May 27, 2023

Improved Privacy-Preserving PCA Using Optimized Homomorphic Matrix Multiplication
Xirong Ma
Principal Component Analysis Homomorphic Encryption Efficient Homomorphic Homomorphic Logistic Regression Training

May 26, 2023

Secure Vertical Federated Learning Under Unreliable Connectivity
Xinchi Qiu, Heng Pan, Wanru Zhao, Yan Gao, Pedro P. B. Gusmao, William F. Shen, Chenyang Ma, Nicholas D. Lane
Homomorphic Encryption Vertical Federated Learning VFL Algorithm

May 23, 2023

Fair Differentially Private Federated Learning Framework
Ayush K. Varshney, Sonakshi Garg, Arka Ghosh, Sargam Gupta
Differential Privacy Homomorphic Encryption Private Federated Learning Private Probabilistic

May 18, 2023

Efficient Vertical Federated Learning with Secure Aggregation
Xinchi Qiu, Heng Pan, Wanru Zhao, Chenyang Ma, Pedro Porto Buarque de Gusmão, Nicholas D. Lane
Homomorphic Encryption Vertical Federated Learning PRIvacy Leakage Secure Aggregation

May 3, 2023

Data Privacy with Homomorphic Encryption in Neural Networks Training and Inference
Ivone Amorim, Eva Maia, Pedro Barbosa, Isabel Praça
Neural Network Scientific Inference Homomorphic Encryption Privacy Guarantee Data Privacy Privacy Sensitive

April 29, 2023

Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learning
Yan Kang, Hanlin Gu, Xingxing Tang, Yuanqin He, Yuzhu Zhang, Jinnan He, Yuxing Han, Lixin Fan, Kai Chen, Qiang Yang
High Efficiency Federated Learning Multi Objective Optimization Homomorphic Encryption Task Utility Inherent Privacy

Homomorphic Encryption

Papers

Privacy-Preserving 3-Layer Neural Network Training

Hyperdimensional Computing as a Rescue for Efficient Privacy-Preserving Machine Learning-as-a-Service

A Homomorphic Encryption Framework for Privacy-Preserving Spiking Neural Networks

Integrating Homomorphic Encryption and Trusted Execution Technology for Autonomous and Confidential Model Refining in Cloud

Blockchain-based Optimized Client Selection and Privacy Preserved Framework for Federated Learning

SecureBoost Hyperparameter Tuning via Multi-Objective Federated Learning

Towards Fast and Scalable Private Inference

Practical Privacy-Preserving Gaussian Process Regression via Secret Sharing

ArctyrEX : Accelerated Encrypted Execution of General-Purpose Applications

High-Resolution Convolutional Neural Networks on Homomorphically Encrypted Data via Sharding Ciphertexts

An Efficient and Multi-private Key Secure Aggregation for Federated Learning

Efficient Skip Connections Realization for Secure Inference on Encrypted Data

FheFL: Fully Homomorphic Encryption Friendly Privacy-Preserving Federated Learning with Byzantine Users

A Meta-learning Framework for Tuning Parameters of Protection Mechanisms in Trustworthy Federated Learning

Improved Privacy-Preserving PCA Using Optimized Homomorphic Matrix Multiplication

Secure Vertical Federated Learning Under Unreliable Connectivity

Fair Differentially Private Federated Learning Framework

Efficient Vertical Federated Learning with Secure Aggregation

Data Privacy with Homomorphic Encryption in Neural Networks Training and Inference

Optimizing Privacy, Utility and Efficiency in Constrained Multi-Objective Federated Learning