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

November 4, 2024

Differentially private and decentralized randomized power method
Julien Nicolas, César Sabater, Mohamed Maouche, Sonia Ben Mokhtar, Mark Coates
Differential Privacy Sensitive Data Secure Aggregation Decentralized FL Decentralized Machine Power Method

October 30, 2024

Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols
Atharv Deshmukh
Native Robustness Secure Aggregation Byzantine Robust Byzantine Attack Population Protocol Byzantine Robust Federated Learning

October 29, 2024

$\mathsf{OPA}$: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning
Harish Karthikeyan, Antigoni Polychroniadou
Interaction Generation Secure Aggregation Individual Perspective Private Aggregation Secure Computation

October 21, 2024

NetSafe: Exploring the Topological Safety of Multi-agent Networks
Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Qingsong Wen, Kun Wang, Yang Wang
LLM Based Secure Aggregation Multi Agent Network Graph Topology

October 13, 2024

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning
Yiwei Zhang, Rouzbeh Behnia, Attila A. Yavuz, Reza Ebrahimi, Elisa Bertino
LeArning Abstract Secure Aggregation Federated Deep

September 2, 2024

Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications
Riccardo Taiello, Sergen Cansiz, Marc Vesin, Francesco Cremonesi, Lucia Innocenti, Melek Önen, Marco Lorenzi
Federated Learning Secure Aggregation Real World Clinical Protecting Privacy

July 27, 2024

On Joint Noise Scaling in Differentially Private Federated Learning with Multiple Local Steps
Mikko A. Heikkilä
Differential Privacy Secure Aggregation Private Federated Learning Joint Denoising Training Data Privacy

July 13, 2024

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models
Shanghao Shi, Md Shahedul Haque, Abhijeet Parida, Marius George Linguraru, Y. Thomas Hou, Syed Muhammad Anwar, Wenjing Lou
Federated Learning Medical Image Secure Aggregation Privacy Inference Adversarial Model

June 22, 2024

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning
Zhibo Wang, Zhiwei Chang, Jiahui Hu, Xiaoyi Pang, Jiacheng Du, Yongle Chen, Kui Ren
Secure Aggregation Gradient Inversion Attack Aggregated Gradient Label Inference Attack Private Label Label Leakage

June 13, 2024

EncCluster: Scalable Functional Encryption in Federated Learning through Weight Clustering and Probabilistic Filters
Vasileios Tsouvalas, Samaneh Mohammadi, Ali Balador, Tanir Ozcelebi, Francesco Flammini, Nirvana Meratnia
Differential Privacy Secure Aggregation Bayesian Filtering Hard Clustering Functional Encryption

June 5, 2024

Buffered Asynchronous Secure Aggregation for Cross-Device Federated Learning
Kun Wang, Yi-Rui Yang, Wu-Jun Li
Secure Aggregation Cross Device Federated Learning Asynchronous Aggregation

June 3, 2024

No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learning
Zhibo Xing, Zijian Zhang, Zi'ang Zhang, Jiamou Liu, Liehuang Zhu, Giovanni Russello
Secure Aggregation Byzantine Robust Zero Knowledge Model Poisoning Attack Byzantine Robust Federated Learning Vandalism Detection

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 13, 2024

Secure Aggregation Meets Sparsification in Decentralized Learning
Sayan Biswas, Anne-Marie Kermarrec, Rafael Pires, Rishi Sharma, Milos Vujasinovic
Decentralized Learning Secure Aggregation Encryption Method Sparsification Method

May 6, 2024

Differentially Private Federated Learning without Noise Addition: When is it Possible?
Jiang Zhang, Konstantinos Psounis, Salman Avestimehr
Secure Aggregation Private Federated Learning Differential Privacy Guarantee

May 3, 2024

FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy
Abdulrahman Diaa, Thomas Humphries, Florian Kerschbaum
Differential Privacy Federated Prompt Cooperation Secure Aggregation K$ Mean Secure Computation Tunable Slack Mechanism

April 21, 2024

FedMPQ: Secure and Communication-Efficient Federated Learning with Multi-codebook Product Quantization
Xu Yang, Jiapeng Zhang, Qifeng Zhang, Zhuo Tang
Codebook Learning Secure Aggregation Communication Compression Multi Codebook FedML Parrot

April 16, 2024

Confidential Federated Computations
Hubert Eichner, Daniel Ramage, Kallista Bonawitz, Dzmitry Huba, Tiziano Santoro, Brett McLarnon, Timon Van Overveldt, Nova Fallen, Peter Kairouz, Albert Cheu, Katharine Daly, Adria Gascon, Marco Gruteser, Brendan McMahan
Differential Privacy Privacy Guarantee Secure Aggregation Federated Setting Privacy Sensitive Secure Multiparty Computation

April 15, 2024

Noiseless Privacy-Preserving Decentralized Learning
Sayan Biswas, Mathieu Even, Anne-Marie Kermarrec, Laurent Massoulie, Rafael Pires, Rishi Sharma, Martijn de Vos
Differential Privacy Industrial Disturbing Noise Decentralized Learning Secure Aggregation Empirical Privacy Virtual Network

March 26, 2024

Secure Aggregation is Not Private Against Membership Inference Attacks
Khac-Hoang Ngo, Johan Östman, Giuseppe Durisi, Alexandre Graell i Amat
Membership Inference Attack Local Differential Privacy Secure Aggregation Privacy Mechanism

Secure Aggregation

Papers

Differentially private and decentralized randomized power method

Byzantine-Robust Federated Learning: An Overview With Focus on Developing Sybil-based Attacks to Backdoor Augmented Secure Aggregation Protocols

$\mathsf{OPA}$: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning

NetSafe: Exploring the Topological Safety of Multi-agent Networks

Uncovering Attacks and Defenses in Secure Aggregation for Federated Deep Learning

Enhancing Privacy in Federated Learning: Secure Aggregation for Real-World Healthcare Applications

On Joint Noise Scaling in Differentially Private Federated Learning with Multiple Local Steps

Harvesting Private Medical Images in Federated Learning Systems with Crafted Models

Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning

EncCluster: Scalable Functional Encryption in Federated Learning through Weight Clustering and Probabilistic Filters

Buffered Asynchronous Secure Aggregation for Cross-Device Federated Learning

No Vandalism: Privacy-Preserving and Byzantine-Robust Federated Learning

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

Secure Aggregation Meets Sparsification in Decentralized Learning

Differentially Private Federated Learning without Noise Addition: When is it Possible?

FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy

FedMPQ: Secure and Communication-Efficient Federated Learning with Multi-codebook Product Quantization

Confidential Federated Computations

Noiseless Privacy-Preserving Decentralized Learning

Secure Aggregation is Not Private Against Membership Inference Attacks