mlsanityData to 14 Oct 2026

DPAUC: Differentially Private AUC Computation in Federated Learning

arXiv 2208.12294 ↗First posted 25 Aug 2022cs.LG cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants. The prior work on FL has mostly studied how to protect label privacy during model training. However, model evaluation in FL might also lead to potential leakage of private label information. In this work, 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. Through extensive experiments, we show our algorithms can compute accurate AUCs compared to the ground truth. The code is available at urlhttps://github.com/bytedance/fedlearner/tree/master/example/privacy/DPAUC.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 25 Aug 2022.

Builds on

25 of 50 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Deep Learning with Differential Privacycited by 2,728
  3. 2019Deep Leakage from Gradientscited by 1,021
  4. 2016Wide & Deep Learning for Recommender Systemscited by 747
  5. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 712
  6. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  7. 2018Split learning for health: Distributed deep learning without sharing raw patient datacited by 395
  8. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  9. 2018Distributed learning of deep neural network over multiple agentscited by 279
  10. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 272
  11. 2021Numerical Composition of Differential Privacycited by 180
  12. 2018Amplification by Shuffling: From Local to Central Differential Privacy via Anonymitycited by 164
13 more
  1. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 123
  2. 2021Deep Learning with Label Differential Privacycited by 117
  3. 2018Distributed Differential Privacy via Shufflingcited by 115
  4. 2020Acceleration for Compressed Gradient Descent in Distributed and Federated Optimizationcited by 90
  5. 2021Label Leakage and Protection in Two-party Split Learningcited by 90
  6. 2020Federated Accelerated Stochastic Gradient Descentcited by 85
  7. 2020Can We Use Split Learning on 1D CNN Models for Privacy Preserving Training?cited by 50
  8. 2020SplitNN-driven Vertical Partitioningcited by 42
  9. 2021Defending against Reconstruction Attack in Vertical Federated Learningcited by 20
  10. 2019Local Differential Privacy: a tutorialcited by 13
  11. 2014Differentially Private Algorithms for Empirical Machine Learningcited by 8
  12. 2022Differentially Private AUC Computation in Vertical Federated Learningcited by 3
  13. 2021Randomized Response Mechanisms for Differential Privacy Data Analysis: Bounds and Applicationscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 2.

7 papers.

  1. 2023Label Inference Attack against Split Learning under Regression Settingcited by 8
  2. 2022Federated Calibration and Evaluation of Binary Classifierscited by 5
  3. 2023PCDP-SGD: Improving the Convergence of Differentially Private SGD via Projection in Advancecited by 2
  4. 2024S2NeRF: Privacy-preserving Training Framework for NeRFcited by 2
  5. 2024Fluent: Round-efficient Secure Aggregation for Private Federated Learningcited by 0
  6. 2025Differential Privacy for Euclidean Jordan Algebra with Applications to Private Symmetric Cone Programmingcited by 0
  7. 2025Federated Computation of ROC and PR Curvescited by 0