Byzantine-Resilient Secure Federated Learning

2020/07/21 by Jinhyun So, So, Jinhyun, Başak Güler +4 · 22 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Cryptography and Data Security #Cryptography and Security (cs.CR) #Distributed #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC) #cs.CR #cs.DC #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.2007.11115

openalex publication_date 2020/07/21 · arxiv created 2021/02/20 · arxiv updated 2021/02/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Secure federated learning is a privacy-preserving framework to improve machine learning models by training over large volumes of data collected by mobile users. This is achieved through an iterative process where, at each iteration, users update a global model using their local datasets. Each user then masks its local model via random keys, and the masked models are aggregated at a central server to compute the global model for the next iteration. As the local models are protected by random masks, the server cannot observe their true values. This presents a major challenge for the resilience of the model against adversarial (Byzantine) users, who can manipulate the global model by modifying their local models or datasets. Towards addressing this challenge, this paper presents the first single-server Byzantine-resilient secure aggregation framework (BREA) for secure federated learning. BREA is based on an integrated stochastic quantization, verifiable outlier detection, and secure model aggregation approach to guarantee Byzantine-resilience, privacy, and convergence simultaneously. We provide theoretical convergence and privacy guarantees and characterize the fundamental trade-offs in terms of the network size, user dropouts, and privacy protection. Our experiments demonstrate convergence in the presence of Byzantine users, and comparable accuracy to conventional federated learning benchmarks.

Citations

• Authenticated Algorithms for Byzantine Agreement
• How to share a secret
• New directions in cryptography
• Differentially Private Federated Learning: A Client Level Perspective
• Agnostic Federated Learning
• Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
• Learning Multiple Layers of Features from Tiny Images
• Advances and Open Problems in Federated Learning

Cited by

• Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
• FLARE: Adaptive Multi-Dimensional Reputation for Robust Client Reliability in Federated Learning
• LSHFed: Robust and Communication-Efficient Federated Learning with Locally-Sensitive Hashing Gradient Mapping
• FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
• H+: An Efficient Similarity-Aware Aggregation for Byzantine Resilient Federated Learning
• EByFTVeS: Efficient Byzantine Fault Tolerant-based Verifiable Secret-sharing in Distributed Privacy-preserving Machine Learning
• Deep Learning based Moving Target Defence for Federated Learning against Poisoning Attack in MEC Systems with a 6G Wireless Model
• Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
• Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
• Federated Learning for Large Models in Medical Imaging: A Comprehensive Review
• Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
• FORTA: Byzantine-Resilient FL Aggregation via DFT-Guided Krum
• Byzantine-resilient federated online learning for Gaussian process regression
• Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
• Detect & Score: Privacy-Preserving Misbehaviour Detection and Contribution Evaluation in Federated Learning
• Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?
• Centroid Approximation for Byzantine-Tolerant Federated Learning
• Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
• Robust Federated Learning against Model Perturbation in Edge Networks
• Privacy-preserving Prompt Personalization in Federated Learning for Multimodal Large Language Models
• Random Client Selection on Contrastive Federated Learning for Tabular Data
• Nosy Layers, Noisy Fixes: Tackling DRAs in Federated Learning Systems using Explainable AI

Related

• Perfect Privacy for Discriminator-Based Byzantine-Resilient Federated Learning
• Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
• Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraints
• Byzantine-Resilient Secure Aggregation for Federated Learning Without Privacy Compromises
• zPROBE: Zero Peek Robustness Checks for Federated Learning