多生成器多判别器框架提升GAN泛化能力，增强对成员推理攻击的防御
MGMD-GAN: Generalization Improvement of Generative Adversarial Networks with Multiple Generator Multiple Discriminator Framework Against Membership Inference Attacks
- 采用多生成器多判别器架构，用数据分区训练以学习混合分布
- 实验显示该模型显著缩小泛化差距，降低成员推理攻击成功率
- 适合关注生成模型隐私安全的研究者和开发者
生成对抗网络（GAN）在多种应用中被广泛使用，但其原始架构可能记忆训练数据分布，从而面临成员推理攻击威胁。本文提出一种新型GAN框架——多生成器多判别器（MGMD-GAN），通过将训练数据划分为互不重叠的子集进行分别训练，使模型学习所有数据子集的混合分布。该设计有效缩小了模型的泛化差距，使其对成员推理攻击更具鲁棒性。我们对所提模型进行了实验分析，并与其它GAN框架进行了对比，验证了其在隐私保护方面的有效性。
原文摘要 · Abstract (English)
Generative Adversarial Networks (GAN) are among the widely used Generative models in various applications. However, the original GAN architecture may memorize the distribution of the training data and, therefore, poses a threat to Membership Inference Attacks. In this work, we propose a new GAN framework that consists of Multiple Generators and Multiple Discriminators (MGMD-GAN). Disjoint partitions of the training data are used to train this model and it learns the mixture distribution of all the training data partitions. In this way, our proposed model reduces the generalization gap which makes our MGMD-GAN less vulnerable to Membership Inference Attacks. We provide an experimental analysis of our model and also a comparison with other GAN frameworks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。