arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.00529cs.LGcs.CRcs.CV
收藏

GRNN:生成回归神经网络--一种针对联邦学习的数据泄漏攻击

GRNN: Generative Regression Neural Network -- A Data Leakage Attack for Federated Learning

Swansea University(斯旺西大学)

Hanchi Ren, Jingjing Deng, Xianghua Xie

摘要:

数据隐私已经成为机器学习(ML)中越来越重要的问题,其中已经开发了许多方法来应对这一挑战,例如密码学(同态加密(HE)、差分隐私(DP)等)。和协作训练(安全多方计算(MPC)、分布式学习和联邦学习(FL))。这些技术特别关注数据加密或安全本地计算。他们将中间信息传输给第三方来计算最终结果。梯度交换通常被认为是在深度学习(DL)中协作训练鲁棒模型的安全方式。然而,最近的研究表明,敏感信息可以从共享梯度中恢复。生成对抗网络(GAN),特别是,已被证明是有效的恢复这些信息。然而,基于GAN的技术需要额外的信息,例如通常不可用于隐私保护学习的类标签。在本文中,我们表明,在FL系统中,基于图像的隐私数据可以很容易地恢复完全共享的梯度,只有通过我们提出的生成回归神经网络(GRNN)。我们将攻击描述为回归问题,并通过最小化梯度之间的距离来优化生成模型的两个分支。我们评估我们的方法在几个图像分类任务。结果表明,我们提出的GRNN优于国家的最先进的方法具有更好的稳定性,更强的鲁棒性,更高的精度。它对全局FL模型也没有收敛要求。此外,我们证明了信息泄漏使用人脸重新识别。在这项工作中还讨论了一些防御策略。

英文摘要:

Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and collaborative training (Secure Multi-Party Computation (MPC), Distributed Learning and Federated Learning (FL)). These techniques have a particular focus on data encryption or secure local computation. They transfer the intermediate information to the third party to compute the final result. Gradient exchanging is commonly considered to be a secure way of training a robust model collaboratively in Deep Learning (DL). However, recent researches have demonstrated that sensitive information can be recovered from the shared gradient. Generative Adversarial Network (GAN), in particular, has shown to be effective in recovering such information. However, GAN based techniques require additional information, such as class labels which are generally unavailable for privacy-preserved learning. In this paper, we show that, in the FL system, image-based privacy data can be easily recovered in full from the shared gradient only via our proposed Generative Regression Neural Network (GRNN). We formulate the attack to be a regression problem and optimize two branches of the generative model by minimizing the distance between gradients. We evaluate our method on several image classification tasks. The results illustrate that our proposed GRNN outperforms state-of-the-art methods with better stability, stronger robustness, and higher accuracy. It also has no convergence requirement to the global FL model. Moreover, we demonstrate information leakage using face re-identification. Some defense strategies are also discussed in this work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑