论文标题
Instahide：用于私人分布式学习的实例隐藏方案
InstaHide: Instance-hiding Schemes for Private Distributed Learning
论文作者
论文摘要
多个分布式实体如何在保留隐私的同时协作在其私人数据上进行共享的深网培训？本文介绍了Instahide，这是对训练图像的简单加密，可以插入现有的分布式深度学习管道中。该加密是有效的，并且在训练期间应用它对测试准确性的影响很小。 Instahide用“一次性秘密键”将每个训练图像加密，其中包括混合许多随机选择的图像并应用随机像素掩码。本文的其他贡献包括：（a）使用大型公共数据集（例如ImageNet）在加密过程中进行混合，从而提高安全性。 （b）实验结果显示在保护已知攻击的隐私方面有效性，对准确性的影响很小。 （c）理论分析表明，成功攻击隐私需要攻击者解决困难的计算问题。 （d）证明使用像素面罩的使用对于安全性很重要，因为仅单独使用混合就对某些有效的攻击没有安全感。 （e）发布挑战数据集https://github.com/hazelsuko07/instahide_challenge 我们的代码可从https://github.com/hazelsuko07/instahide获得
How can multiple distributed entities collaboratively train a shared deep net on their private data while preserving privacy? This paper introduces InstaHide, a simple encryption of training images, which can be plugged into existing distributed deep learning pipelines. The encryption is efficient and applying it during training has minor effect on test accuracy. InstaHide encrypts each training image with a "one-time secret key" which consists of mixing a number of randomly chosen images and applying a random pixel-wise mask. Other contributions of this paper include: (a) Using a large public dataset (e.g. ImageNet) for mixing during its encryption, which improves security. (b) Experimental results to show effectiveness in preserving privacy against known attacks with only minor effects on accuracy. (c) Theoretical analysis showing that successfully attacking privacy requires attackers to solve a difficult computational problem. (d) Demonstrating that use of the pixel-wise mask is important for security, since Mixup alone is shown to be insecure to some some efficient attacks. (e) Release of a challenge dataset https://github.com/Hazelsuko07/InstaHide_Challenge Our code is available at https://github.com/Hazelsuko07/InstaHide
