Secure Aggregation

Ask about this topic

Overview

Secure aggregation studies how federated clients can reveal a sum, average, or other combined statistic while hiding their individual updates from a server or other participants. Common approaches use pairwise masks and secret sharing, multiparty computation, or homomorphic encryption; some add differential privacy, dropout recovery, or verifiable and Byzantine-robust aggregation. Work spans cross-silo settings such as healthcare and finance as well as large-scale federated learning, where communication, latency, and client churn shape protocol design. A central tension is that stronger privacy and robustness can raise costs, and hiding individual updates does not by itself prevent inference from topology, collusion, or the released aggregate.

Latest papers

CardsList

19 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. Fundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated Learning

    Oct 19, 2026Jinbao Zhu, Kai Wan, Giuseppe CaireSecure AggregationPrivacy-Preserving ML

    Information Coding and Transmission (ICT) Key Laboratory of Sichuan Province, Southwest Jiaotong University, Chengdu 611756, China · School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China · Electrical Engineering and Computer Science Department, Technische Universität Berlin, 10587 Berlin, Germany

  2. Progressive-Resolution Secure Aggregation for Federated Learning

    Sep 30, 2026Seyed Mohammad Azimi-AbarghouyiFederated Learning AggregationSecure Aggregation

    Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden

  3. When Topology Betrays Privacy: Lattice-Based Reconstruction Attacks on Secure Aggregation in Decentralized Federated Learning

    Sep 8, 2026Wenrui Yu, Changlong Ji, Johannes Bjerva +1Federated Learning AggregationSecure Aggregation

    Aalborg University Copenhagen, Denmark · Institut Polytechnique de Paris Paris, France

  4. Pushing Forward Multi-Secret-Key Homomorphic Encryption for Private Average Aggregation

    Sep 1, 2026Miguel Morona-Mínguez, Fernando Pérez-González, Alberto Pedrouzo-UlloaFederated Learning AggregationHomomorphic Encryption

    aatlanTTic, Universidade de Vigo, Escola de Enxeñaría de Telecomunicación, Vigo, 36310, Galicia, Spain

  5. Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data

    Jul 30, 2026Pouya Rajabi, Mohsen TooraniFederated Learning AggregationPrivacy-Preserving ML

    Department of Science and Industry Systems University of South-Eastern Norway Kongsberg, Norway

  6. MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics

    Jul 27, 2026Paul Largillier, Karl Paygambar, Cédric Gouy-Pailler +3Privacy-Preserving MLGenomics

    Université Paris-Saclay, CEA, LIST, France · Université Paris-Saclay, CEA, CNRGH, France

  7. Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries

    Jul 23, 2026Hyeong-Gun Joo, Songnam Hong, Dong-Joon ShinSecure Multi-Party ComputationFederated Learning Aggregation

    Department of Electronic Engineering, Hanyang University, Seoul, South Korea

  8. PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning

    Jul 7, 2026Harsh Kasyap, Anil Kumar Pradhan, Ugur Ilker Atmaca +2Federated Learning AggregationByzantine-Robust Federated Learning

    Indian Institute of Technology (BHU), Varanasi, India · University of Warwick, Coventry, UK · Vaulttree,, Ireland +2

  9. Quantum ring all-reduce: communication and privacy advantages for distributed learning

    Jun 18, 2026María Gragera Garcés, Lirandë PiraCommunication-Efficient Distributed TrainingPrivacy-Preserving ML

    University of Edinburgh, Edinburgh, United Kingdom · Centre for Quantum Technologies, National University of Singapore, Singapore

  10. Giskard : Byzantine Robust and Private Aggregation for Large-Scale Decentralized Learning

    Jun 17, 2026Ousmane Touat, César Sabater, Mohamed Maouche +1Secure Multi-Party ComputationCommunication-Efficient Distributed Training

    INSA Lyon, LIRIS, CNRS, Villeurbanne, France · INRIA, INSA Lyon, Villeurbanne, France

  11. Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning

    Jun 9, 2026Hengxuan Tang, Jinbao Zhu, Xiaohu TangFederated Learning AggregationCommunication-Efficient Distributed Training

    Southwest Jiaotong University

  12. The Capacity of Information-Theoretic Secure Aggregation in Federated Learning

    Jun 5, 2026Lanxin Yi, Jinbao Zhu, Kai Wan +1Federated Learning AggregationPrivacy-Preserving ML

    Information Coding and Transmission (ICT) Key Laboratory of Sichuan Province, Southwest Jiaotong University, Chengdu 611756, China · School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan 430074, China

  13. Echelon: Auditable Aggregate-Only Language-Model Adaptation Across Privacy Boundaries

    Jun 1, 2026Hina Dixit, Punit Kumar, Irene Tenison +1Privacy-Preserving Language ModelsCommunication-Efficient Distributed Training

    Decompute Inc., Cupertino

  14. DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

    May 13, 2026Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos +4Federated Learning AggregationCommunication-Efficient Distributed Training

    Samsung R&D Institute UK (SRUK) · Information Technologies Institute (CERTH-ITI)

  15. Scalable and Verifiable Federated Learning for Cross-Institution Financial Fraud Detection

    Apr 25, 2026Prajwal Panth, Nishant NigamFederated Learning AggregationCommunication-Efficient Distributed Training

    School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, India · School of Electronics Engineering, KIIT Deemed to be University, Bhubaneswar, India

  16. Combinatorial Privacy: Private Multi-Party Bitstream Grand Sum by Hiding in Birkhoff Polytopes

    Mar 24, 2026Praneeth VepakommaSecure Multi-Party ComputationSecure Aggregation

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · Massachusetts Institute of Technology (MIT)

  17. TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+)

    Mar 20, 2026Harish Karthikeyan, Antigoni PolychroniadouSecure AggregationSecure Multi-Party Computation

    JPMorgan AI Research, JPMorgan AlgoCRYPT CoE

  18. FedVideoMAE: Efficient Federated Video Moderation with Differential Privacy and Secure Aggregation

    Dec 21, 2025Ziyuan Tao, Chuanzhi Xu, Sandaru Jayawardana +4Federated Learning AggregationVideo Content Moderation

    School of Computing, Macquarie University, Sydney, Australia · School of Computer Science, The University of Sydney, Sydney, Australia · School of Electrical and Computer Engineering, The University of Sydney, Sydney, Australia

  19. Federated Computation of ROC and PR Curves

    Oct 6, 2025Xuefeng Xu, Graham CormodePrivacy-Preserving MLSecure Aggregation

    University of Warwick