Differentially Private Cross-camera Person Re-identification
This addresses privacy concerns for individuals in surveillance systems, though it is incremental as it builds on existing differential privacy techniques.
The paper tackles the privacy risks in camera-based person re-identification by introducing a differential privacy mechanism using pixelisation and colour quantisation to distort images, resulting in significantly reduced adverse task performances while maintaining high re-identification accuracy.
Camera-based person re-identification is a heavily privacy-invading task by design, benefiting from rich visual data to match together person representations across different cameras. This high-dimensional data can then easily be used for other, perhaps less desirable, applications. We here investigate the possibility of protecting such image data against uses outside of the intended re-identification task, and introduce a differential privacy mechanism leveraging both pixelisation and colour quantisation for this purpose. We show its ability to distort images in such a way that adverse task performances are significantly reduced, while retaining high re-identification performances.