基于混淆的隐私保护表示可通过邻域信息恢复
Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Information
AI总结：
针对AR/VR/MR等应用中隐私保护定位的几何混淆技术，本文揭示其可通过邻域信息恢复原始点位置的弱点，并提出学习邻域共现描述符的恢复方法，实验证明该方法适用于现有所有几何混淆方案。
摘要：
AR/VR/MR应用和基于云的视觉定位系统的快速普及，使得人们越来越关注定位过程中用户内容的隐私问题。深度神经网络能够从稀疏的3D或2D点集及其描述符中恢复场景的详细图像（即所谓的反转攻击），进一步加剧了这一隐私担忧。因此，隐私保护定位的研究重点是防止对查询图像关键点和场景地图的3D点的反转攻击。为此，已有几种几何混淆技术被提出，例如将点提升到更高维空间（如直线或平面），或在点之间交换坐标。在本文中，我们指出这些混淆方法存在一个共同弱点：在已知邻域的假设下，可以恢复原始点位置的近似值。我们进一步证明，可以通过学习识别邻域中共现的描述符来计算这些邻域。大量实验表明，我们的点恢复方法实际上适用于所有现有的几何混淆方案。我们的结果表明，尽管这些方案声称具有隐私保护性，但不应将其视为隐私保护的。代码将在https://github.com/kunalchelani/RecoverPointsNeighborhood上提供。
英文摘要：
Rapid growth in the popularity of AR/VR/MR applications and cloud-based visual localization systems has given rise to an increased focus on the privacy of user content in the localization process. This privacy concern has been further escalated by the ability of deep neural networks to recover detailed images of a scene from a sparse set of 3D or 2D points and their descriptors - the so-called inversion attacks. Research on privacy-preserving localization has therefore focused on preventing these inversion attacks on both the query image keypoints and the 3D points of the scene map. To this end, several geometry obfuscation techniques that lift points to higher-dimensional spaces, i.e., lines or planes, or that swap coordinates between points % have been proposed. In this paper, we point to a common weakness of these obfuscations that allows to recover approximations of the original point positions under the assumption of known neighborhoods. We further show that these neighborhoods can be computed by learning to identify descriptors that co-occur in neighborhoods. Extensive experiments show that our approach for point recovery is practically applicable to all existing geometric obfuscation schemes. Our results show that these schemes should not be considered privacy-preserving, even though they are claimed to be privacy-preserving. Code will be available at https://github.com/kunalchelani/RecoverPointsNeighborhood.
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。
