SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination-猫眼课题宝

DOI：

10.48550/arxiv.2207.12263

发表时间：

2022-07

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Zhu-rong Yuan;Fan Wu;Yunhui Long;Chaowei Xiao;Bo Li

通过使用预训练模型进行迁移学习已成为机器学习社区的增长趋势。因此，许多预先训练的模型被在线发布以促进进一步的研究。然而，人们普遍担心这些预先训练的模型是否会泄露其训练数据的隐私敏感信息。因此，在这项工作中，我们旨在回答以下问题：“我们能否有效地从这些预训练模型中恢复私人信息？检索此类敏感信息的充分条件是什么？”我们首先探索可以将私人训练分布与其他分布区分开来的不同统计信息。根据我们的观察，我们提出了一种新颖的隐私数据重建框架 SecretGen，以有效地恢复隐私信息。与之前通过目标恢复实例的真实预测来恢复隐私数据的方法相比，SecretGen 不需要这种先验知识，使其更加实用。我们在不同场景下的不同数据集上进行了大量实验，将 SecretGen 与其他基线进行比较，并提供系统基准，以更好地理解不同辅助信息和优化操作的影响。我们表明，在没有关于真实类别预测的先验知识的情况下，SecretGen 能够以与利用此类先验知识的数据相似的性能恢复私有数据。如果给出先验知识，SecretGen 将显着优于基线方法。我们还提出了一些定量指标来进一步量化预训练模型的隐私漏洞，这将有助于隐私敏感应用程序的模型选择。我们的代码位于：https://github.com/AI-secure/SecretGen。

Transfer learning through the use of pre-trained models has become a growing trend for the machine learning community. Consequently, numerous pre-trained models are released online to facilitate further research. However, it raises extensive concerns on whether these pre-trained models would leak privacy-sensitive information of their training data. Thus, in this work, we aim to answer the following questions:"Can we effectively recover private information from these pre-trained models? What are the sufficient conditions to retrieve such sensitive information?"We first explore different statistical information which can discriminate the private training distribution from other distributions. Based on our observations, we propose a novel private data reconstruction framework, SecretGen, to effectively recover private information. Compared with previous methods which can recover private data with the ground true prediction of the targeted recovery instance, SecretGen does not require such prior knowledge, making it more practical. We conduct extensive experiments on different datasets under diverse scenarios to compare SecretGen with other baselines and provide a systematic benchmark to better understand the impact of different auxiliary information and optimization operations. We show that without prior knowledge about true class prediction, SecretGen is able to recover private data with similar performance compared with the ones that leverage such prior knowledge. If the prior knowledge is given, SecretGen will significantly outperform baseline methods. We also propose several quantitative metrics to further quantify the privacy vulnerability of pre-trained models, which will help the model selection for privacy-sensitive applications. Our code is available at: https://github.com/AI-secure/SecretGen.

SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination

文献摘要

相似文献