A Privacy-Preserving Multi-Task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition.

Clicks: 374
ID: 89969
2019
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #18 of 124 articles by views in frontiers in neurorobotics

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 124 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Recently, multi-task learning (MTL) has been extensively studied for various face processing tasks, including face detection, landmark localization, pose estimation, and gender recognition. This approach endeavors to train a better model by exploiting the synergy among the related tasks. However, the raw face dataset used for training often contains sensitive and private information, which can be maliciously recovered by carefully analyzing the model and outputs. To address this problem, we propose a novel privacy-preserving multi-task learning approach that utilizes the differential private stochastic gradient descent algorithm to optimize the end-to-end multi-task model and weighs the loss functions of multiple tasks to improve learning efficiency and prediction accuracy. Specifically, calibrated noise is added to the gradient of loss functions to preserve the privacy of the training data during model training. Furthermore, we exploit the homoscedastic uncertainty to balance different learning tasks. The experiments demonstrate that the proposed approach yields differential privacy guarantees without decreasing the accuracy of HyperFace under a desirable privacy budget.
Reference Key
zhang2019afrontiers Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Zhang, Chen;Hu, Xiongwei;Xie, Yu;Gong, Maoguo;Yu, Bin;
Journal frontiers in neurorobotics
Year 2019
DOI
10.3389/fnbot.2019.00112
URL
Keywords
multi-task learning balance different learning tasks differential privacy guarantees differential private stochastic gradient descent privacy preserving

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.