Differentially Private AUC Computation in Vertical Federated Learning

• URL: http://arxiv.org/abs/2205.12412v1
• Date: Tue, 24 May 2022 23:46:21 GMT
• Title: Differentially Private AUC Computation in Vertical Federated Learning
• Authors: Jiankai Sun and Xin Yang and Yuanshun Yao and Junyuan Xie and Di Wu and Chong Wang
• Abstract summary: We propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL. Through extensive experiments, we show our algorithms can achieve more accurate AUCs compared to the baselines.
• Score: 21.692648490368327
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning has gained great attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple parties. As a sub-category, vertical federated learning (vFL) focuses on the scenario where features and labels are split into different parties. The prior work on vFL has mostly studied how to protect label privacy during model training. However, model evaluation in vFL might also lead to potential leakage of private label information. One mitigation strategy is to apply label differential privacy (DP) but it gives bad estimations of the true (non-private) metrics. In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL. Through extensive experiments, we show our algorithms can achieve more accurate AUCs compared to the baselines.

Related papers

• Stalactite: Toolbox for Fast Prototyping of Vertical Federated Learning Systems [37.11550251825938]
  We present emphStalactite - an open-source framework for Vertical Federated Learning (VFL) systems. VFL is a type of FL where data samples are divided by features across several data owners. We demonstrate its use on a real-world recommendation datasets.
  arXiv  Detail & Related papers  (2024-09-23T21:29:03Z)
• ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations [26.310416723272184]
  Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations by sharing training parameters instead of raw data. adversaries can still infer individual information through inference attacks on these training parameters. Differential Privacy (DP) has been widely used in FL to prevent such attacks. We consider differentially private federated learning in a resource-constrained scenario, where both privacy budget and communication rounds are constrained.
  arXiv  Detail & Related papers  (2023-08-21T04:09:59Z)
• Can Public Large Language Models Help Private Cross-device Federated Learning? [58.05449579773249]
  We study (differentially) private federated learning (FL) of language models. Public data has been used to improve privacy-utility trade-offs for both large and small language models. We propose a novel distribution matching algorithm with theoretical grounding to sample public data close to private data distribution.
  arXiv  Detail & Related papers  (2023-05-20T07:55:58Z)
• Label Inference Attack against Split Learning under Regression Setting [24.287752556622312]
  We study the leakage in the scenario of the regression model, where the private labels are continuous numbers. We propose a novel learning-based attack that integrates gradient information and extra learning regularization objectives.
  arXiv  Detail & Related papers  (2023-01-18T03:17:24Z)
• Scalable Collaborative Learning via Representation Sharing [53.047460465980144]
  Federated learning (FL) and Split Learning (SL) are two frameworks that enable collaborative learning while keeping the data private (on device) In FL, each data holder trains a model locally and releases it to a central server for aggregation. In SL, the clients must release individual cut-layer activations (smashed data) to the server and wait for its response (during both inference and back propagation). In this work, we present a novel approach for privacy-preserving machine learning, where the clients collaborate via online knowledge distillation using a contrastive loss.
  arXiv  Detail & Related papers  (2022-11-20T10:49:22Z)
• DPAUC: Differentially Private AUC Computation in Federated Learning [21.692648490368327]
  Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. We propose an evaluation algorithm that can accurately compute the widely used AUC (area under the curve) metric when using the label differential privacy (DP) in FL.
  arXiv  Detail & Related papers  (2022-08-25T18:29:11Z)
• FairVFL: A Fair Vertical Federated Learning Framework with Contrastive Adversarial Learning [102.92349569788028]
  We propose a fair vertical federated learning framework (FairVFL) to improve the fairness of VFL models. The core idea of FairVFL is to learn unified and fair representations of samples based on the decentralized feature fields in a privacy-preserving way. For protecting user privacy, we propose a contrastive adversarial learning method to remove private information from the unified representation in server.
  arXiv  Detail & Related papers  (2022-06-07T11:43:32Z)
• A Coupled Design of Exploiting Record Similarity for Practical Vertical Federated Learning [47.77625754666018]
  Federated learning is a learning paradigm to enable collaborative learning across different parties without revealing raw data. Most existing studies in vertical federated learning disregard the "record linkage" process. We design a novel coupled training paradigm, FedSim, that integrates one-to-many linkage into the training process.
  arXiv  Detail & Related papers  (2021-06-11T11:09:53Z)
• Voting-based Approaches For Differentially Private Federated Learning [87.2255217230752]
  This work is inspired by knowledge transfer non-federated privacy learning from Papernot et al. We design two new DPFL schemes, by voting among the data labels returned from each local model, instead of averaging the gradients. Our approaches significantly improve the privacy-utility trade-off over the state-of-the-arts in DPFL.
  arXiv  Detail & Related papers  (2020-10-09T23:55:19Z)
• Hybrid Differentially Private Federated Learning on Vertically Partitioned Data [41.7896466307821]
  We present HDP-VFL, the first hybrid differentially private (DP) framework for vertical federated learning (VFL) We analyze how VFL's intermediate result (IR) can leak private information of the training data during communication. We mathematically prove that our algorithm not only provides utility guarantees for VFL, but also offers multi-level privacy.
  arXiv  Detail & Related papers  (2020-09-06T16:06:04Z)
• Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models [67.66144604972052]
  Federated learning (FL) is a promising way to use the computing power of mobile devices while maintaining privacy of users. We show that a critical issue that affects the test accuracy is the large gradient diversity of the models from different users. We propose a novel grouping-based model averaging method to replace the FedAvg averaging method.
  arXiv  Detail & Related papers  (2020-08-26T03:36:07Z)

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.