mlsanityData to 7 Oct 2026

LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning

arXiv 2109.14236 ↗First posted 29 Sep 2021cs.LG cs.CR cs.DCcited by 63

Not on the map. Why?

Abstract (arXiv)

Secure model aggregation is a key component of federated learning (FL) that aims at protecting the privacy of each user's individual model while allowing for their global aggregation. It can be applied to any aggregation-based FL approach for training a global or personalized model. Model aggregation needs to also be resilient against likely user dropouts in FL systems, making its design substantially more complex. State-of-the-art secure aggregation protocols rely on secret sharing of the random-seeds used for mask generations at the users to enable the reconstruction and cancellation of those belonging to the dropped users. The complexity of such approaches, however, grows substantially with the number of dropped users. We propose a new approach, named LightSecAgg, to overcome this bottleneck by changing the design from "random-seed reconstruction of the dropped users" to "one-shot aggregate-mask reconstruction of the active users via mask encoding/decoding". We show that LightSecAgg achieves the same privacy and dropout-resiliency guarantees as the state-of-the-art protocols while significantly reducing the overhead for resiliency against dropped users. We also demonstrate that, unlike existing schemes, LightSecAgg can be applied to secure aggregation in the asynchronous FL setting. Furthermore, we provide a modular system design and optimized on-device parallelization for scalable implementation, by enabling computational overlapping between model training and on-device encoding, as well as improving the speed of concurrent receiving and sending of chunked masks. We evaluate LightSecAgg via extensive experiments for training diverse models on various datasets in a realistic FL system with large number of users and demonstrate that LightSecAgg significantly reduces the total training time.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 39 of its 69 references that are in the map. First posted on arXiv 29 Sep 2021.

Builds on

39 of 69 references.

References · 39

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  5. 2019Searching for MobileNetV3cited by 1,984
  6. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  7. 2020Adaptive Federated Optimizationcited by 1,036
  8. 2019Deep Leakage from Gradientscited by 1,004
  9. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  10. 2019Towards Federated Learning at Scale: System Designcited by 826
  11. 2018LEAF: A Benchmark for Federated Settingscited by 780
  12. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
27 more
  1. 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 665
  2. 2020Personalized Federated Learning with Moreau Envelopescited by 612
  3. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
  4. 2021A Field Guide to Federated Optimizationcited by 312
  5. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 305
  6. 2019Asynchronous Federated Optimizationcited by 264
  7. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  8. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  9. 2020Learning from History for Byzantine Robust Optimizationcited by 137
  10. 2020LDP-Fed: Federated Learning with Local Differential Privacycited by 129
  11. 2020UVeQFed: Universal Vector Quantization for Federated Learningcited by 103
  12. 2020Byzantine-Resilient Secure Federated Learningcited by 93
  13. 2020Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learningcited by 78
  14. 2018Lagrange Coded Computing: Optimal Design for Resiliency, Security and Privacycited by 66
  15. 2020FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learningcited by 60
  16. 2021Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learningcited by 38
  17. 2019Central Server Free Federated Learning over Single-sided Trust Social Networkscited by 33
  18. 2020Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Searchcited by 30
  19. 2021SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networkscited by 30
  20. 2019Federated Learning with Autotuned Communication-Efficient Secure Aggregationcited by 23
  21. 2020Asynchronous Federated Learning with Reduced Number of Rounds and with Differential Privacy from Less Aggregated Gaussian Noisecited by 21
  22. 2019CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learningcited by 20
  23. 2021Information Theoretic Secure Aggregation with User Dropoutscited by 19
  24. 2021Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detectioncited by 19
  25. 2020Secure Byzantine-Robust Machine Learningcited by 18
  26. 2021Basil: A Fast and Byzantine-Resilient Approach for Decentralized Trainingcited by 13
  27. 2021OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 21; 2024: 13; 2025: 15; 2026: 6.

63 papers.

Sort:

By area:

  1. 2023FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning Systemcited by 38
  2. 2023LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulationcited by 35
  3. 2023GPT-FL: Generative Pre-trained Model-Assisted Federated Learningcited by 24
  4. 2022Machine Unlearning of Federated Clusterscited by 21
  5. 2021CodedPaddedFL and CodedSecAgg: Straggler Mitigation and Secure Aggregation in Federated Learningcited by 20
  6. 2022How Much Privacy Does Federated Learning with Secure Aggregation Guarantee?cited by 19
  7. 2022SwiftAgg+: Achieving Asymptotically Optimal Communication Loads in Secure Aggregation for Federated Learningcited by 18
  8. 2023FLINT: A Platform for Federated Learning Integrationcited by 17
  9. 2023FedVS: Straggler-Resilient and Privacy-Preserving Vertical Federated Learning for Split Modelscited by 17
  10. 2023FedGT: Identification of Malicious Clients in Federated Learning with Secure Aggregationcited by 16
  11. 2023Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learningcited by 16
  12. 2022SwiftAgg: Communication-Efficient and Dropout-Resistant Secure Aggregation for Federated Learning with Worst-Case Security Guaranteescited by 14
38 more
  1. 2023Fusion of Global and Local Knowledge for Personalized Federated Learningcited by 14
  2. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  3. 2024Towards Federated RLHF with Aggregated Client Preference for LLMscited by 11
  4. 2023Federated Learning Across Decentralized and Unshared Archives for Remote Sensing Image Classificationcited by 10
  5. 2023Federated Analytics: A surveycited by 9
  6. 2023The Resource Problem of Using Linear Layer Leakage Attack in Federated Learningcited by 9
  7. 2025Fundamental Limits of Hierarchical Secure Aggregation with Cyclic User Associationcited by 7
  8. 2023Fake It Till Make It: Federated Learning with Consensus-Oriented Generationcited by 6
  9. 2023Proof-of-Contribution-Based Design for Collaborative Machine Learning on Blockchaincited by 5
  10. 2023Private Aggregation in Hierarchical Wireless Federated Learning with Partial and Full Collusioncited by 5
  11. 2024Worldwide Federated Training of Language Modelscited by 5
  12. 2024Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learningcited by 5
  13. 2023Efficient Node Selection in Private Personalized Decentralized Learningcited by 4
  14. 2023ByzSecAgg: A Byzantine-Resistant Secure Aggregation Scheme for Federated Learning Based on Coded Computing and Vector Commitmentcited by 4
  15. 2023Secure Vertical Federated Learning Under Unreliable Connectivitycited by 4
  16. 2024DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Imagescited by 4
  17. 2024Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimationcited by 4
  18. 2025FedMVP: Federated Multimodal Visual Prompt Tuning for Vision-Language Modelscited by 4
  19. 2023PriPrune: Quantifying and Preserving Privacy in Pruned Federated Learningcited by 3
  20. 2021Location Leakage in Federated Signal Mapscited by 2
  21. 2024NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQAcited by 2
  22. 2025Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusioncited by 2
  23. 2025Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resiliencecited by 2
  24. 2025The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods for Federated Learningcited by 2
  25. 2023Fed-Safe: Securing Federated Learning in Healthcare Against Adversarial Attackscited by 1
  26. 2025AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregatorcited by 1
  27. 2025ModShift: Model Privacy via Designed Shiftscited by 1
  28. 2025DictPFL: Efficient and Private Federated Learning on Encrypted Gradientscited by 1
  29. 2025Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learningcited by 1
  30. 2026Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Datacited by 1
  31. 2022Generalized Lagrange Coded Computing: A Flexible Computation-Communication Tradeoff for Resilient, Secure, and Private Computationcited by 0
  32. 2022Secure Embedding Aggregation for Federated Representation Learningcited by 0
  33. 2023An Efficient and Multi-private Key Secure Aggregation for Federated Learningcited by 0
  34. 2023MetisFL: An Embarrassingly Parallelized Controller for Scalable & Efficient Federated Learning Workflowscited by 0
  35. 2024Chu-ko-nu: A Reliable, Efficient, and Anonymously Authentication-Enabled Realization for Multi-Round Secure Aggregation in Federated Learningcited by 0
  36. 2024Privacy-Preserving, Dropout-Resilient Aggregation in Decentralized Learningcited by 0
  37. 2024Differentially Private Federated Learning without Noise Addition: When is it Possible?cited by 0
  38. 2024Buffered Asynchronous Secure Aggregation for Cross-Device Federated Learningcited by 0

50 most cited of 63 All 63 (JSON)