Privacy-Preserving Digital Capture
Sophisticated mobile computing, sensing and recording devices like smartphones and Google Glass are carried by their users virtually around the clock, thus blurring the distinction between the online and offline worlds. While these devices enable transformative new applications and services, they also introduce entirely new threats to users’ privacy, because they can capture a complete record of the user’s location, online and offline activities, and social encounters, including an audiovisual record. In this project, we aim to protect users’ privacy in the presence of mobile and wearable devices with recording capabilities. As a basic building block, we will develop privacy-preserving mechanisms to associate a network communication endpoint with robust signatures of the user which can be based e.g. on the visual appearance or the voice of the user. Using such a mechanism, a device can advertise, via the Internet or short-range radio (e.g. Bluetooth), a signature of its owner’s appearance. The challenge lies on the one hand to develop signatures and corresponding mechanisms that allow to robustly identify the device’s owner in a photo or video, yet, without such a recording, are insufficient to identify the owner, or track the owner across repeated encounters. A mechanism with this capability can be used as follows.
A device can advertise to nearby devices its owner’s signature along with the device owner’s privacy preferences. A preference may state, for instance, that the owner wishes to have her face blurred in any photo or video taken by other devices. We will develop an architecture that enables the platform software on mobile devices (Android, iOS, Windows Phone) to enforce these privacy preferences independent of applications. Additionally, based on the same principles, we will research ways to also protect “privacy” of objects.
Role Within the Collaborative Research Center