Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning

• URL: http://arxiv.org/abs/2410.11368v1
• Date: Tue, 15 Oct 2024 07:45:18 GMT
• Title: Secure Stateful Aggregation: A Practical Protocol with Applications in Differentially-Private Federated Learning
• Authors: Marshall Ball, James Bell-Clark, Adria Gascon, Peter Kairouz, Sewoong Oh, Zhiye Xie,
• Abstract summary: DP-FTRL based approaches have already seen widespread deployment in industry. We introduce secure stateful aggregation: a simple append-only data structure that allows for the private storage of aggregate values. We observe that secure stateful aggregation suffices for realizing DP-FTRL-based private federated learning.
• Score: 36.42916779389165
• License:
• Abstract: Recent advances in differentially private federated learning (DPFL) algorithms have found that using correlated noise across the rounds of federated learning (DP-FTRL) yields provably and empirically better accuracy than using independent noise (DP-SGD). While DP-SGD is well-suited to federated learning with a single untrusted central server using lightweight secure aggregation protocols, secure aggregation is not conducive to implementing modern DP-FTRL techniques without assuming a trusted central server. DP-FTRL based approaches have already seen widespread deployment in industry, albeit with a trusted central curator who provides and applies the correlated noise. To realize a fully private, single untrusted server DP-FTRL federated learning protocol, we introduce secure stateful aggregation: a simple append-only data structure that allows for the private storage of aggregate values and reading linear functions of the aggregates. Assuming Ring Learning with Errors, we provide a lightweight and scalable realization of this protocol for high-dimensional data in a new security/resource model, Federated MPC : where a powerful persistent server interacts with weak, ephemeral clients. We observe that secure stateful aggregation suffices for realizing DP-FTRL-based private federated learning: improving DPFL utility guarantees over the state of the art while maintaining privacy with an untrusted central party. Our approach has minimal overhead relative to existing techniques which do not yield comparable utility. The secure stateful aggregation primitive and the federated MPC paradigm may be of interest for other practical applications.

Related papers

• DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning using Packed Secret Sharing [51.336015600778396]
  Federated Learning (FL) has gained lots of traction recently, both in industry and academia. In FL, a machine learning model is trained using data from various end-users arranged in committees across several rounds. Since such data can often be sensitive, a primary challenge in FL is providing privacy while still retaining utility of the model.
  arXiv  Detail & Related papers  (2024-10-21T16:25:14Z)
• Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence [22.946928984205588]
  Differentially private federated learning (DP-FL) is a promising technique for collaborative model training. We propose the first DP-FL framework (namely UDP-FL) which universally harmonizes any randomization mechanism. We show that UDP-FL exhibits substantial resilience against different inference attacks.
  arXiv  Detail & Related papers  (2024-07-20T00:11:59Z)
• Correlated Privacy Mechanisms for Differentially Private Distributed Mean Estimation [8.660393575612169]
  CorDP-DME is a novel DP-DME that spans the gap between local differential privacy (LDP) and distributed DP (SecAgg) We provide an information-theoretic analysis of CorDP-DME, and derive theoretical guarantees for utility under any given privacy parameters.
  arXiv  Detail & Related papers  (2024-07-03T17:22:33Z)
• FastLloyd: Federated, Accurate, Secure, and Tunable $k$-Means Clustering with Differential Privacy [26.927356987142407]
  We study the problem of privacy-preserving $k$-means clustering in the horizontally federated setting. Existing approaches using secure computation suffer from substantial overheads and do not offer output privacy. By utilizing the computational DP model, we design a lightweight, secure aggregation-based approach that achieves four orders of magnitude speed-up.
  arXiv  Detail & Related papers  (2024-05-03T19:04:37Z)
• FedMPQ: Secure and Communication-Efficient Federated Learning with Multi-codebook Product Quantization [12.83265009728818]
  We propose a novel uplink communication compression method for federated learning, named FedMPQ. In contrast to previous works, our approach exhibits greater robustness in scenarios where data is not independently and identically distributed. Experiments conducted on the LEAF dataset demonstrate that our proposed method achieves 99% of the baseline's final accuracy.
  arXiv  Detail & Related papers  (2024-04-21T08:27:36Z)
• Federated Nearest Neighbor Machine Translation [66.8765098651988]
  In this paper, we propose a novel federated nearest neighbor (FedNN) machine translation framework. FedNN leverages one-round memorization-based interaction to share knowledge across different clients. Experiments show that FedNN significantly reduces computational and communication costs compared with FedAvg.
  arXiv  Detail & Related papers  (2023-02-23T18:04:07Z)
• Differentially Private Federated Bayesian Optimization with Distributed Exploration [48.9049546219643]
  We introduce differential privacy (DP) into the training of deep neural networks through a general framework for adding DP to iterative algorithms. We show that DP-FTS-DE achieves high utility (competitive performance) with a strong privacy guarantee. We also use real-world experiments to show that DP-FTS-DE induces a trade-off between privacy and utility.
  arXiv  Detail & Related papers  (2021-10-27T04:11:06Z)
• Federated Learning with Sparsification-Amplified Privacy and Adaptive Optimization [27.243322019117144]
  Federated learning (FL) enables distributed agents to collaboratively learn a centralized model without sharing their raw data with each other. We propose a new FL framework with sparsification-amplified privacy. Our approach integrates random sparsification with gradient perturbation on each agent to amplify privacy guarantee.
  arXiv  Detail & Related papers  (2020-08-01T20:22:57Z)
• User-Level Privacy-Preserving Federated Learning: Analysis and Performance Optimization [77.43075255745389]
  Federated learning (FL) is capable of preserving private data from mobile terminals (MTs) while training the data into useful models. From a viewpoint of information theory, it is still possible for a curious server to infer private information from the shared models uploaded by MTs. We propose a user-level differential privacy (UDP) algorithm by adding artificial noise to the shared models before uploading them to servers.
  arXiv  Detail & Related papers  (2020-02-29T10:13:39Z)
• CryptoSPN: Privacy-preserving Sum-Product Network Inference [84.88362774693914]
  We present a framework for privacy-preserving inference of sum-product networks (SPNs) CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.
  arXiv  Detail & Related papers  (2020-02-03T14:49:18Z)

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.