Data to 14 Oct 2026

Practical Secure Aggregation for Federated Learning on User-Held Data

arXiv 1611.04482 ↗First posted 14 Nov 2016cs.CR stat.MLcited by 178

Not on the map. Why?

Abstract (arXiv)

Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregation protects each user's model gradient. We design a novel, communication-efficient Secure Aggregation protocol for high-dimensional data that tolerates up to 1/3 users failing to complete the protocol. For 16-bit input values, our protocol offers 1.73x communication expansion for 210 users and 220-dimensional vectors, and 1.98x expansion for 214 users and 224 dimensional vectors.

Key facts. Cited by 178 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 35; 2022: 26; 2023: 37; 2024: 32; 2025: 29; 2026: 19.

178 papers.

Sort:

By area:

2021Evaluating Gradient Inversion Attacks and Defenses in Federated Learningcited by 196
2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
2021Federated Learning for Smart Healthcare: A Surveycited by 184
2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 128
2024Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Modelscited by 116
2022FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extractioncited by 102
2021Papaya: Practical, Private, and Scalable Federated Learningcited by 90
2021Federated Evaluation and Tuning for On-Device Personalization: System Design & Applicationscited by 85
2022Recovering Private Text in Federated Learning of Language Modelscited by 70
2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 69
2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41

38 more

2023A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Taskscited by 41
2023Federated Learning for Computationally-Constrained Heterogeneous Devices: A Surveycited by 40
2021FedCG: Leverage Conditional GAN for Protecting Privacy and Maintaining Competitive Performance in Federated Learningcited by 39
2022The Fundamental Price of Secure Aggregation in Differentially Private Federated Learningcited by 39
2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
2021GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learningcited by 36
2022Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Datacited by 36
2021FedCV: A Federated Learning Framework for Diverse Computer Vision Taskscited by 32
2021Towards Model Agnostic Federated Learning Using Knowledge Distillationcited by 31
2023On the Convergence of Federated Averaging with Cyclic Client Participationcited by 31
2022Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learningcited by 30
2024The Future of Large Language Model Pre-training is Federatedcited by 30
2022Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning using Independent Component Analysiscited by 29
2024PrE-Text: Training Language Models on Private Federated Data in the Age of LLMscited by 29
2023On the Privacy-Robustness-Utility Trilemma in Distributed Learningcited by 24
2023GPT-FL: Generative Pre-trained Model-Assisted Federated Learningcited by 24
2023Grounding Foundation Models through Federated Transfer Learning: A General Frameworkcited by 24
2023Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimationcited by 22
2021User-Level Label Leakage from Gradients in Federated Learningcited by 21
2021Information Theoretic Secure Aggregation with User Dropoutscited by 19
2021Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligencecited by 18
2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
2023Privacy-Aware Document Visual Question Answeringcited by 17
2021A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guaranteecited by 16
2024Text-Enhanced Data-free Approach for Federated Class-Incremental Learningcited by 16
2022Secure Aggregation for Federated Learning in Flowercited by 15
2023Privacy-preserving quantum federated learning via gradient hidingcited by 15
2024SPEAR:Exact Gradient Inversion of Batches in Federated Learningcited by 15
2024FedFisher: Leveraging Fisher Information for One-Shot Federated Learningcited by 15
2022SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guaranteescited by 14
2023Fusion of Global and Local Knowledge for Personalized Federated Learningcited by 14
2025POPri: Private Federated Learning using Preference-Optimized Synthetic Datacited by 14
2021Privacy and Trust Redefined in Federated Machine Learningcited by 13
2024Towards Federated RLHF with Aggregated Client Preference for LLMscited by 13
2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
2022Unbounded Gradients in Federated Learning with Buffered Asynchronous Aggregationcited by 12
2023BAFFLE: A Baseline of Backpropagation-Free Federated Learningcited by 12
2024FedFa: A Fully Asynchronous Training Paradigm for Federated Learningcited by 12

50 most cited of 178 All 178 (JSON)