Secret Sharing

Secret sharing is a cryptographic technique enabling distributed storage and computation of sensitive data without revealing individual components. Current research focuses on improving the efficiency and security of secret sharing within various machine learning contexts, particularly federated learning and multi-party computation, employing techniques like Shamir's secret sharing and function secret sharing to enhance privacy and robustness against attacks (e.g., poisoning, Byzantine failures, and inference attacks). These advancements are crucial for enabling secure and private collaborative machine learning across diverse applications, including healthcare, finance, and IoT, where data privacy is paramount.

Papers

October 21, 2024

DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning using Packed Secret Sharing
Alexander Bienstock, Ujjwal Kumar, Antigoni Polychroniadou
LeArning Abstract Differential Privacy Privacy Utility Secret Sharing Unfolded D ADMM Cryptographic Protocol Differentially Private Federated Learning

July 6, 2024

Robust Skin Color Driven Privacy Preserving Face Recognition via Function Secret Sharing
Dong Han, Yufan Jiang, Yong Li, Ricardo Mendes, Joachim Denzler
Generative Adversarial Network Face Image Secret Sharing Privacy Preserving Face

June 21, 2024

Supersonic OT: Fast Unconditionally Secure Oblivious Transfer
Aydin Abadi, Yvo Desmedt
Secure Multi Party Computation Secret Sharing Oblivious Transfer Cryptographic Protocol

June 4, 2024

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud
Shijin Duan, Chenghong Wang, Hongwu Peng, Yukui Luo, Wujie Wen, Caiwen Ding, Xiaolin Xu
Machine Learning Cloud Computing Practical Application Secret Sharing Party Computation Secure Deep

May 24, 2024

RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
Peihua Mai, Ran Yan, Yan Pang
Federated Learning Poisoning Attack Secure Aggregation Robust Aggregation Robust Federated Learning Secret Sharing

May 14, 2024

Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises
Yue Xia, Christoph Hofmeister, Maximilian Egger, Rawad Bitar
Calysto Scheme Privacy Preserving Computation Secret Sharing Byzantine Robust Aggregation Byzantine Robust Method

April 27, 2024

Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning
Ali Reza Ghavamipour, Benjamin Zi Hao Zhao, Fatih Turkmen
Decentralized Learning Structured Dropout Inference Attack Secret Sharing Decentralized Aggregation

April 14, 2024

Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learning
Tanveer Khan, Mindaugas Budzys, Antonis Michalas
Split Learning PRIvacy Leakage Split and Fit Secret Sharing Encrypted Model Feature Space Hijacking Attack Hijacking Task

March 10, 2024

Fluent: Round-efficient Secure Aggregation for Private Federated Learning
Xincheng Li, Jianting Ning, Geong Sen Poh, Leo Yu Zhang, Xinchun Yin, Tianwei Zhang
Secure Aggregation Private Federated Learning Secret Sharing

February 23, 2024

Chu-ko-nu: A Reliable, Efficient, and Anonymously Authentication-Enabled Realization for Multi-Round Secure Aggregation in Federated Learning
Kaiping Cui, Xia Feng, Liangmin Wang, Haiqin Wu, Xiaoyu Zhang, Boris Düdder
High Efficiency Secure Aggregation Zero Knowledge Secret Sharing

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

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

April 26, 2023

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models
Songze Li, Duanyi Yao, Jin Liu
Vertical Federated Learning Model Privacy Secret Sharing Model Splitting VFL Algorithm Information Theoretic Privacy

February 20, 2023

ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitment
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Giuseppe Caire
Secure Aggregation Secret Sharing Secure Computation Byzantine Robust Aggregation Commitment Mechanism Coded Computing

February 10, 2023

On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence
Daphnee Chabal, Dolly Sapra, Zoltán Ádám Mann
Deep Neural Network Privacy Preserving Edge Computing Edge AI Edge Intelligence Secret Sharing

October 1, 2022

Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph
Yang Lu, Zhengxin Yu, Neeraj Suri
Decentralized Federated Learning Model Aggregation Federated Learning Framework Communication Graph Average Consensus Secret Sharing

March 22, 2022

SPRITE: A Scalable Privacy-Preserving and Verifiable Collaborative Learning for Industrial IoT
Jayasree Sengupta, Sushmita Ruj, Sipra Das Bit
Privacy Preserving Resource Constrained Industrial Internet of Thing Secret Sharing Verifiable Learning

February 8, 2022

SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li, Giuseppe Caire
Federated Learning Worst Case Secure Aggregation Secret Sharing

January 17, 2022

EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Party
Yimin Huang, Xinyu Feng, Wanwan Wang, Hao He, Yukun Wang, Ming Yao
Homomorphic Encryption Vertical Federated Learning Secret Sharing Passive Party

December 16, 2021

CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learning
Reent Schlegel, Siddhartha Kumar, Eirik Rosnes, Alexandre Graell i Amat
Secure Aggregation Zero Padding Straggler Mitigation Secret Sharing Gradient Coding

Secret Sharing

Papers

DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning using Packed Secret Sharing

Robust Skin Color Driven Privacy Preserving Face Recognition via Function Secret Sharing

Supersonic OT: Fast Unconditionally Secure Oblivious Transfer

SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud

RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation

Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises

Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learning

Make Split, not Hijack: Preventing Feature-Space Hijacking Attacks in Split Learning

Fluent: Round-efficient Secure Aggregation for Private Federated Learning

Chu-ko-nu: A Reliable, Efficient, and Anonymously Authentication-Enabled Realization for Multi-Round Secure Aggregation in Federated Learning

Practical Privacy-Preserving Gaussian Process Regression via Secret Sharing

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

FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Models

ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitment

On Achieving Privacy-Preserving State-of-the-Art Edge Intelligence

Privacy-preserving Decentralized Federated Learning over Time-varying Communication Graph

SPRITE: A Scalable Privacy-Preserving and Verifiable Collaborative Learning for Industrial IoT

SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guarantees

EFMVFL: An Efficient and Flexible Multi-party Vertical Federated Learning without a Third Party

CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learning