Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings
This addresses privacy concerns for users of cloud-based vision systems like visual localization and face authentication, though it is an incremental improvement over existing privacy-preserving methods.
The paper tackles the privacy risk of image features in cloud-based computer vision by proposing a new representation that embeds features in adversarial affine subspaces, making it significantly harder for adversaries to recover sensitive information while enabling feature matching via subspace distances.
Many computer vision systems require users to upload image features to the cloud for processing and storage. These features can be exploited to recover sensitive information about the scene or subjects, e.g., by reconstructing the appearance of the original image. To address this privacy concern, we propose a new privacy-preserving feature representation. The core idea of our work is to drop constraints from each feature descriptor by embedding it within an affine subspace containing the original feature as well as adversarial feature samples. Feature matching on the privacy-preserving representation is enabled based on the notion of subspace-to-subspace distance. We experimentally demonstrate the effectiveness of our method and its high practical relevance for the applications of visual localization and mapping as well as face authentication. Compared to the original features, our approach makes it significantly more difficult for an adversary to recover private information.