Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees

• URL: http://arxiv.org/abs/2205.11765v2
• Date: Sat, 18 Mar 2023 18:33:56 GMT
• Title: Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees
• Authors: Banghua Zhu, Lun Wang, Qi Pang, Shuai Wang, Jiantao Jiao, Dawn Song, Michael I. Jordan
• Abstract summary: We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. We benchmark against competing protocols and show the empirical superiority of the proposed protocols. Our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server.
• Score: 123.0401978870009
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose Byzantine-robust federated learning protocols with nearly optimal statistical rates. In contrast to prior work, our proposed protocols improve the dimension dependence and achieve a tight statistical rate in terms of all the parameters for strongly convex losses. We benchmark against competing protocols and show the empirical superiority of the proposed protocols. Finally, we remark that our protocols with bucketing can be naturally combined with privacy-guaranteeing procedures to introduce security against a semi-honest server. The code for evaluation is provided in https://github.com/wanglun1996/secure-robust-federated-learning.

Related papers

• Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains [3.3748750222488657]
  Cross-silo federated learning allows data owners to train accurate machine learning models by benefiting from each others private datasets. To incentivize client participation in privacy-sensitive domains, a FL protocol should strike a delicate balance between privacy guarantees and end-model accuracy. We study the question of when and how a server could design a FL protocol provably beneficial for all participants.
  arXiv  Detail & Related papers  (2024-03-11T12:43:44Z)
• Statistical evaluation and optimization of entanglement purification protocols [0.0]
  We demonstrate that pioneering protocols are unable to improve the estimated initial average concurrence of almost uniformly sampled density matrices. We also develop a more efficient protocol and investigate it numerically together with a recent proposal based on an entangling rank-$2$ projector.
  arXiv  Detail & Related papers  (2024-02-19T16:58:03Z)
• TernaryVote: Differentially Private, Communication Efficient, and Byzantine Resilient Distributed Optimization on Heterogeneous Data [50.797729676285876]
  We propose TernaryVote, which combines a ternary compressor and the majority vote mechanism to realize differential privacy, gradient compression, and Byzantine resilience simultaneously. We theoretically quantify the privacy guarantee through the lens of the emerging f-differential privacy (DP) and the Byzantine resilience of the proposed algorithm.
  arXiv  Detail & Related papers  (2024-02-16T16:41:14Z)
• A Survey of Secure Computation Using Trusted Execution Environments [80.58996305474842]
  This article provides a systematic review and comparison of TEE-based secure computation protocols. We first propose a taxonomy that classifies secure computation protocols into three major categories, namely secure outsourced computation, secure distributed computation and secure multi-party computation. Based on these criteria, we review, discuss and compare the state-of-the-art TEE-based secure computation protocols for both general-purpose computation functions and special-purpose ones.
  arXiv  Detail & Related papers  (2023-02-23T16:33:56Z)
• Semi-quantum private comparison and its generalization to the key agreement, summation, and anonymous ranking [12.16288190962638]
  Semi-quantum protocols construct connections between quantum users and classical'' users who can only perform certain classical'' operations. We present a new semi-quantum private comparison protocol based on entangled states and single particles.
  arXiv  Detail & Related papers  (2022-10-07T09:40:36Z)
• Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond [57.10914865054868]
  We consider vertical logistic regression (VLR) trained with mini-batch descent gradient. We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks.
  arXiv  Detail & Related papers  (2022-07-19T05:47:30Z)
• Data post-processing for the one-way heterodyne protocol under composable finite-size security [62.997667081978825]
  We study the performance of a practical continuous-variable (CV) quantum key distribution protocol. We focus on the Gaussian-modulated coherent-state protocol with heterodyne detection in a high signal-to-noise ratio regime. This allows us to study the performance for practical implementations of the protocol and optimize the parameters connected to the steps above.
  arXiv  Detail & Related papers  (2022-05-20T12:37:09Z)
• Discrete-variable quantum key distribution with homodyne detection [14.121646217925441]
  We propose a protocol that combines the simplicity of quantum state preparation in DV-QKD together with the cost-effective and high-bandwidth of homodyne detectors used in CV-QKD. Our simulation suggests that the protocol is suitable for secure and high-speed practical key distribution over distances.
  arXiv  Detail & Related papers  (2021-09-01T17:12:28Z)
• Selective Classification via One-Sided Prediction [54.05407231648068]
  One-sided prediction (OSP) based relaxation yields an SC scheme that attains near-optimal coverage in the practically relevant high target accuracy regime. We theoretically derive bounds generalization for SC and OSP, and empirically we show that our scheme strongly outperforms state of the art methods in coverage at small error levels.
  arXiv  Detail & Related papers  (2020-10-15T16:14:27Z)
• Efficient Sparse Secure Aggregation for Federated Learning [0.20052993723676896]
  We adapt compression-based federated techniques to additive secret sharing, leading to an efficient secure aggregation protocol. We prove its privacy against malicious adversaries and its correctness in the semi-honest setting. Compared to prior works on secure aggregation, our protocol has a lower communication and adaptable costs for a similar accuracy.
  arXiv  Detail & Related papers  (2020-07-29T14:28:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.