Ensuring Data Privacy in Deep Learning through Compressive Learning

通过压缩学习确保深度学习中的数据隐私

• 批准号: EP/X03447X/1
• 负责人: Matthew Nunes
• 金额: $ 10.13万
• 依托单位: University of Bath
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FX03447X%2F1
• 关键词: Ensuring; Data; Privacy; Deep; Learning

Recent years have seen the wide application of deep learning algorithms in a collaborative setting where multiple participants contribute to the training process of the algorithm. For example, users may submit images to be used collectively to train a machine learning model for image classification. A major concern of collaborative learning is protecting privacy of the participants; this could refer to concealing either their identity or the data they provide. In many cases, we want to make sure that data cannot be directly associated with a specific individual when the model or updates to the model are shared.In this proposal, we will develop new methods to learn deep learning models with differential privacy (DP) guarantee using compressive learning approaches. We will work with a dataset that concerns AI-assisted video content moderation, in which deep-learning based segmentation and classification models have been used to identify explicit image content in the videos and to suggest appropriate levels (moderate, severe etc) for such content. The proposed research avoid the drawbacks of current approaches as well as achieve lower computational cost and be applicable in more general data and analysis scenarios. it will thus remove current computational barriers of applying private deep learning for AI-assisted video content moderation at scale. Being able to guarantee that the content of individual training images are private will help minimize the risk that content is leaked and thus that younger age groups are exposed to unsuitable leaked content.

近年来，深度学习算法在多个参与者参与算法训练过程的协作环境中得到了广泛应用。例如，用户可以提交要集体使用的图像，以训练用于图像分类的机器学习模型。协作学习的一个主要问题是保护参与者的隐私；这可能指的是隐藏他们的身份或他们提供的数据。在许多情况下，当共享模型或模型更新时，我们希望确保数据不能直接与特定个体相关联。在该方案中，我们将开发新的方法来学习具有不同隐私(DP)保证的深度学习模型。我们将使用一个与人工智能辅助的视频内容审核有关的数据集，其中基于深度学习的分割和分类模型已被用于识别视频中的显性图像内容，并为此类内容建议适当的级别(中等、严重等)。所提出的研究避免了现有方法的缺点，同时实现了较低的计算代价，适用于更一般的数据和分析场景。因此，它将消除目前将私人深度学习应用于人工智能辅助的视频内容大规模审核的计算障碍。能够保证个人训练图像的内容是私人的，将有助于将内容被泄露的风险降至最低，从而使较年轻的年龄段暴露在不合适的泄露内容中。