arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.04668cs.CR
收藏

一种用于分布式图像分类的安全指纹框架

A Secure Fingerprinting Framework for Distributed Image Classification

Guowen Xu, Xingshuo Han, Anguo Zhang, Tianwei Zhang

摘要:

深度学习(DL)技术已被广泛用于许多场景中的图像分类,例如,面部识别和嫌疑人追踪这样一个高度商业化的应用,引发了对其DL模式的知识产权保护。为了解决这个问题,主流的方法是在训练过程中将唯一的水印嵌入到目标模型中。然而,现有的努力集中在检测版权侵权的一个给定的模型,而很少考虑的问题,叛徒跟踪。此外,水印嵌入过程可能以分布式方式引起训练数据的隐私问题。在本文中,我们提出了SECUREMARK-DL,一个新的指纹识别框架,以解决上述两个问题,在分布式学习环境。它为每个客户在目标模型中嵌入一个唯一的指纹,一旦出现争议,可以从任何可疑模型中提取和验证。此外,在训练过程中采用了一种新的隐私划分技术,以保护训练数据的隐私。大量的实验证明了SECUREMARK-DL对各种攻击的鲁棒性,以及即使将长位(304位)指纹嵌入到输入图像中也具有高分类准确率(> 95%)。

英文摘要:

The deep learning (DL) technology has been widely used for image classification in many scenarios, e.g., face recognition and suspect tracking. Such a highly commercialized application has given rise to intellectual property protection of its DL model. To combat that, the mainstream method is to embed a unique watermark into the target model during the training process. However, existing efforts focus on detecting copyright infringement for a given model, while rarely consider the problem of traitors tracking. Moreover, the watermark embedding process can incur privacy issues for the training data in a distributed manner. In this paper, we propose SECUREMARK-DL, a novel fingerprinting framework to address the above two problems in a distributed learning environment. It embeds a unique fingerprint into the target model for each customer, which can be extracted and verified from any suspicious model once a dispute arises. In addition, it adopts a new privacy partitioning technique in the training process to protect the training data privacy. Extensive experiments demonstrate the robustness of SECUREMARK-DL against various attacks, and its high classification accuracy (> 95%) even if a long-bit (304-bit) fingerprint is embedded into an input image.

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。

↑