mlsanityData to 7 Oct 2026

Efficient Differentially Private Secure Aggregation for Federated Learning via Hardness of Learning with Errors

arXiv 2112.06872 ↗First posted 13 Dec 2021cs.CR cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Federated machine learning leverages edge computing to develop models from network user data, but privacy in federated learning remains a major challenge. Techniques using differential privacy have been proposed to address this, but bring their own challenges -- many require a trusted third party or else add too much noise to produce useful models. Recent advances in secure aggregation using multiparty computation eliminate the need for a third party, but are computationally expensive especially at scale. We present a new federated learning protocol that leverages a novel differentially private, malicious secure aggregation protocol based on techniques from Learning With Errors. Our protocol outperforms current state-of-the art techniques, and empirical results show that it scales to a large number of parties, with optimal accuracy for any differentially private federated learning scheme.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 21 of its 58 references that are in the map. First posted on arXiv 13 Dec 2021.

Builds on

21 of 58 references.

References · 21

  1. 2019Advances and Open Problems in Federated Learningcited by 3,021
  2. 2016Deep Learning with Differential Privacycited by 2,682
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  5. 2017Renyi Differential Privacycited by 643
  6. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  7. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 471
  8. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  9. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 266
  10. 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 208
  11. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 163
  12. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
9 more
  1. 2018Protection Against Reconstruction and Its Applications in Private Federated Learningcited by 127
  2. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  3. 2018Distributed Differential Privacy via Shufflingcited by 115
  4. 2019Deep Learning with Gaussian Differential Privacycited by 112
  5. 2020Revisiting Membership Inference Under Realistic Assumptionscited by 108
  6. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  7. 2020POSEIDON: Privacy-Preserving Federated Neural Network Learningcited by 23
  8. 2020A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergencescited by 21
  9. 2018Shrinkwrap: Differentially-Private Query Processing in Private Data Federationscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 5; 2026: 6.

23 papers.

Sort:

  1. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 16
  2. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
  3. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 13
  4. 2023Spectral-DP: Differentially Private Deep Learning through Spectral Perturbation and Filteringcited by 6
  5. 2024Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimationcited by 4
  6. 2023Federated Learning: A Cutting-Edge Survey of the Latest Advancements and Applicationscited by 3
  7. 2025A Survey on Cloud-Edge-Terminal Collaborative Intelligence in AIoT Networkscited by 3
  8. 2024The Power of Bias: Optimizing Client Selection in Federated Learning with Heterogeneous Differential Privacycited by 2
  9. 2023Generalizing Differentially Private Decentralized Deep Learning with Multi-Agent Consensuscited by 1
  10. 2024On Using Secure Aggregation in Differentially Private Federated Learning with Multiple Local Stepscited by 1
  11. 2023When approximate design for fast homomorphic computation provides differential privacy guaranteescited by 0
  12. 2023Differentially Private Secure Multiplication: Hiding Information in the Rubble of Noisecited by 0
11 more
  1. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  2. 2024Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learningcited by 0
  3. 2025A Selective Homomorphic Encryption Approach for Faster Privacy-Preserving Federated Learningcited by 0
  4. 2025Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Modelscited by 0
  5. 2025ParaAegis: Parallel Protection for Flexible Privacy-preserved Federated Learningcited by 0
  6. 2026SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacycited by 0
  7. 2026Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregationcited by 0
  8. 2026Secure and Privacy-Preserving Vertical Federated Learningcited by 0
  9. 2026Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Costcited by 0
  10. 2026Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learningcited by 0
  11. 2026When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learningcited by 0