On the Design of Privacy-Aware Cameras: a Study on Deep Neural Networks
This addresses privacy protection for individuals in surveillance or public camera systems, but it is incremental as it builds on existing Privacy by Design concepts with specific camera distortions.
The paper tackled the problem of preventing misuse of private data from camera images by studying the effect of camera distortions, such as out-of-focus and grayscale images, on deep neural networks used for data extraction. They proved that a privacy-aware camera can be built to block extraction of personal information like license plate numbers while still allowing non-sensitive data extraction.
In spite of the legal advances in personal data protection, the issue of private data being misused by unauthorized entities is still of utmost importance. To prevent this, Privacy by Design is often proposed as a solution for data protection. In this paper, the effect of camera distortions is studied using Deep Learning techniques commonly used to extract sensitive data. To do so, we simulate out-of-focus images corresponding to a realistic conventional camera with fixed focal length, aperture, and focus, as well as grayscale images coming from a monochrome camera. We then prove, through an experimental study, that we can build a privacy-aware camera that cannot extract personal information such as license plate numbers. At the same time, we ensure that useful non-sensitive data can still be extracted from distorted images. Code is available at https://github.com/upciti/privacy-by-design-semseg .