Deep generative models, such as Generative Adversarial Networks (GANs), synthesize diverse high-fidelity data samples by estimating the underlying distribution of high dimensional data. Despite their success, GANs may disclose private information from the data they are trained on, making them susceptible to adversarial attacks such as membership inference attacks, in which an adversary aims to determine if a record was part of the training set. We propose an information theoretically motivated regularization term that prevents the generative model from overfitting to training data and encourages generalizability. We show that this penalty minimizes the JensenShannon divergence between components of the generator trained on data with different membership, and that it can be implemented at low cost using an additional classifier. Our experiments on image datasets demonstrate that with the proposed regularization, which comes at only a small added computational cost, GANs are able to preserve privacy and generate high-quality samples that achieve better downstream classification performance compared to non-private and differentially private generative models.
翻译:深基因模型,如基因反转网(GANs),通过估计高维数据的基本分布,综合了多种高忠诚度数据样本。尽管这些模型取得了成功,但全球网络可以从它们所培训的数据中披露私人信息,使其容易受到对抗性攻击,如会籍推断攻击,其中对手的目的是确定记录是否为培训数据集的一部分。我们提出了一个具有理论动机的信息正规化术语,防止基因模型过分适应培训数据,并鼓励通用性。我们表明,这一处罚最大限度地缩小了接受过不同成员数据培训的生成器各组成部分之间的Jensen-hannon差异,并且可以使用额外的分类器以低成本实施这一处罚。我们在图像数据集方面的实验表明,随着拟议的正规化(仅增加少量计算成本),全球网络能够保护隐私并产生高质量的样本,从而比非私营和有差异的私人基因描述模型更能实现更好的下游分类性性性工作。