Secure Aggregation

Secure aggregation (SA) aims to enable collaborative model training in federated learning (FL) without revealing individual client data to the central server. Current research focuses on developing efficient and robust SA protocols, often incorporating cryptographic techniques like homomorphic encryption or secret sharing, and addressing vulnerabilities to various attacks, including gradient inversion and membership inference. The effectiveness and practicality of SA are crucial for deploying privacy-preserving FL in sensitive applications like healthcare and finance, driving ongoing efforts to improve its efficiency, security, and compatibility with different model architectures and data distributions.

Papers

June 28, 2022

Secure Forward Aggregation for Vertical Federated Neural Networks
Shuowei Cai, Di Chai, Liu Yang, Junxue Zhang, Yilun Jin, Leye Wang, Kun Guo, Kai Chen
Neural Network Deep Model Vertical Federated Learning Secure Aggregation Neural Network Framework

May 26, 2022

Encoded Gradients Aggregation against Gradient Leakage in Federated Learning
Dun Zeng, Shiyu Liu, Siqi Liang, Zonghang Li, Hui Wang, Irwin King, Zenglin Xu
Homomorphic Encryption Secure Aggregation Gradient Leakage Aggregated Gradient

May 12, 2022

Secure Aggregation for Federated Learning in Flower
Kwing Hei Li, Pedro Porto Buarque de Gusmão, Daniel J. Beutel, Nicholas D. Lane
Federated Learning Secure Aggregation Threat Model Training Compute

May 11, 2022

Blockchain-based Secure Client Selection in Federated Learning
Truc Nguyen, Phuc Thai, Tre' R. Jeter, Thang N. Dinh, My T. Thai
Secure Aggregation Client Selection Blockchain Transaction

March 24, 2022

SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learning
Tayyebeh Jahani-Nezhad, Mohammad Ali Maddah-Ali, Songze Li, Giuseppe Caire
Federated Learning Privacy Preserving Secure Aggregation SWIFT DynGFN Optimal Communication

March 7, 2022

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
Wei-Ning Chen, Christopher A. Choquette-Choo, Peter Kairouz, Ananda Theertha Suresh
Differential Privacy Secure Aggregation Private Federated Learning Communication Cost O$ Sample

February 15, 2022

OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsification
Fumiyuki Kato, Yang Cao, Masatoshi Yoshikawa
Federated Learning High Quality Risk Description Secure Aggregation Random Sparsification Inference Attack Privacy Preserving Federated Learning Trusted Execution Environment Olive Oil Manufacturing

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

February 7, 2022

Preserving Privacy and Security in Federated Learning
Truc Nguyen, My T. Thai
Homomorphic Encryption Security Related Secure Aggregation Zero Knowledge Privacy Enhancing Technology

January 19, 2022

SCOTCH: An Efficient Secure Computation Framework for Secure Aggregation
Yash More, Prashanthi Ramachandran, Priyam Panda, Arup Mondal, Harpreet Virk, Debayan Gupta
Differential Privacy Secure Aggregation Federated Learning Framework Decentralized Manner Secure Computation

December 23, 2021

Sparsified Secure Aggregation for Privacy-Preserving Federated Learning
Irem Ergun, Hasin Us Sami, Basak Guler
Secure Aggregation

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

December 13, 2021

Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors
Timothy Stevens, Christian Skalka, Christelle Vincent, John Ring, Samuel Clark, Joseph Near
LeArning Abstract High Efficiency Differential Privacy Secure Aggregation Hardness Result Federated Setting Party Computation

November 14, 2021

Eluding Secure Aggregation in Federated Learning via Model Inconsistency
Dario Pasquini, Danilo Francati, Giuseppe Ateniese
Secure Aggregation Private Training Consistent Model Attribution Attack

November 3, 2021

Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation
Eugene Bagdasaryan, Peter Kairouz, Stefan Mellem, Adrià Gascón, Kallista Bonawitz, Deborah Estrin, Marco Gruteser
Differential Privacy Secure Aggregation Decentralized Data Location Heatmaps