Practical Secure Aggregation for Privacy-Preserving Machine Learning

Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).

We design a novel, communication-efficient, failure-robust protocol for secure aggregation of high-dimensional data. Our protocol allows a server to compute the sum of large, user-held data vectors from mobile devices in a secure manner (i.e. without learning each user's individual contribution), and can be used, for example, in a federated learning setting, to aggregate user-provided model updates for a deep neural network. We prove the security of our protocol in the honest-but-curious and active adversary settings, and show that security is maintained even if an arbitrarily chosen subset of users drop out at any time. We evaluate the efficiency of our protocol and show, by complexity analysis and a concrete implementation, that its runtime and communication overhead remain low even on large data sets and client pools. For 16-bit input values, our protocol offers $1.73 x communication expansion for 210 users and 220-dimensional vectors, and 1.98 x expansion for 214 users and 224-dimensional vectors over sending data in the clear.

Last synced 2026-08-22 14:19 UTC

• A Multi-Layer Auditable Vertical Federated Learning Prototype for Power Equipment Supply Chains: Reproducibility, Robustness, and Privacy-Boundary Evaluation

  IoT 2026 · 0 citations

• Privacy-Preserving Federated Learning for Artistic Image Classification in Visual IoT Sensor Networks

  Sensors 2026 · 0 citations

• VCFedAdam: A Verifiable and Compressed FedAdam Aggregation Scheme for Federated Learning in Distributed Sensor Networks

  Sensors 2026 · 0 citations

• RetFL: a privacy-preserving and traceable framework for robust federated learning

  Journal of King Saud University - Computer and Information Sciences 2026 · 0 citations

• Distribution-Aware Personalised Aggregation for Federated Deep Learning Under Non-IID Data

  Applied Sciences 2026 · 0 citations

• A Comprehensive Review on Federated and Incremental Learning in Spatial Crowdsourcing Systems

  Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery 2026 · 0 citations

• Federated and Differentially Private Learning for Root Cause Classification Across Heterogeneous Semiconductor Fabs

  Electronics 2026 · 0 citations

• Current Research and Open Gaps in Federated Large Language Models: A Systematic Review

  SBC Reviews on Computer Science 2026 · 0 citations

• LLMDPA: pre-execution privacy auditing of DP-SGD via evidence-constrained semantic analysis

  Cybersecurity 2026 · 0 citations

• A Study on Trustworthy Aggregation Mechanisms for Blockchain-Based Federated Learning

  Frontiers in Computing and Intelligent Systems 2026 · 0 citations

• Janus: Dual-Sided Communication and Privacy Optimization for Federated Learning in Autonomous Vehicles

  Journal of Trends in Computer Science and Smart Technology 2026 · 0 citations

• Privacy-Preserving Federated Artificial Intelligence for Cross-Institutional Anti-Money Laundering Detection in the United States: A Review

  Cureus Journal of Computer Science. 2026 · 0 citations

• Federated learning with adaptive reliability aware aggregation for privacy preserving healthcare IoT systems

  Scientific Reports 2026 · 0 citations

• Federated and Privacy-Preserving Machine Learning: Methods and Trade-offs

  Eduschool International Journal of Data Science and Machine learning (EIJDSML) 2026 · 0 citations

• FedVIB–AGP: defending against distributed backdoor attacks in federated learning via variational information bottleneck and activation-gap pruning

  Journal of King Saud University - Computer and Information Sciences 2026 · 0 citations

• FedSTIP-Tuning: Federated Black-Box Prompt Tuning with Aggregate-Only Feedback and Common-Candidate Optimization

  Applied Sciences 2026 · 0 citations

• Privacy-Aware AI-Based Fraud Detection and Prevention Framework for Secure UPI and Digital Banking Transactions in India

  International Journal of Advanced Research in Science Communication and Technology 2026 · 0 citations

• Trust-aware adaptive differential privacy for asynchronous federated learning in non-terrestrial networks

  Discover Computing 2026 · 0 citations

• Federated Machine Learning for Privacy-preserving Data Analytics in Distributed Systems

  ETDT 2026 · 0 citations

• Personalized and differentially private federated learning for mobility data mining via the TrajectoryGuard framework

  PLoS ONE 2026 · 0 citations