arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1911.01769cs.CRcs.CVeess.IV
收藏

通过映射失真的视觉隐私保护

Visual Privacy Protection via Mapping Distortion

Tsinghua University(清华大学);Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);Peng Cheng Laboratory(鹏城实验室)

Yiming Li, Peidong Liu, Yong Jiang, Shu-Tao Xia

摘要:

隐私保护是一个重要的研究领域,在这个大数据时代尤为关键。在很大程度上,视觉分类数据的隐私性主要体现在图像与其对应标签之间的映射,因为这种关系提供了大量的信息,并且可以用于其他场景。在本文中,我们提出了基于映射失真的保护(MDP)及其基于增强的扩展(AugMDP),以保护数据隐私,通过修改原始数据集。在MDP生成的修改后的数据集中,图像和它的标签并不一致($e.g.$,一个类似猫的图像被标记为狗),而在其上训练的DNN仍然可以在良性测试集上取得良好的性能。因此,该方法可以在数据集泄露时保护隐私。通过大量的实验验证了该方法的有效性和可行性。用于再现主要结果的代码可在\url{https://github.com/PerdonLiu/Visual-Privacy-Protection-via-Mapping-Distortion}上获得。

英文摘要:

Privacy protection is an important research area, which is especially critical in this big data era. To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios. In this paper, we propose the mapping distortion based protection (MDP) and its augmentation-based extension (AugMDP) to protect the data privacy by modifying the original dataset. In the modified dataset generated by MDP, the image and its label are not consistent ($e.g.$, a cat-like image is labeled as the dog), whereas the DNNs trained on it can still achieve good performance on benign testing set. As such, this method can protect privacy when the dataset is leaked. Extensive experiments are conducted, which verify the effectiveness and feasibility of our method. The code for reproducing main results is available at \url{https://github.com/PerdonLiu/Visual-Privacy-Protection-via-Mapping-Distortion}.

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。

↑