I-Privacy Lab

The goal of this project is to overcome the following challenges which have not been well studied: (i) Privacy protection for human subjects and sensitive objects in the background of the images which are usually ignored by the existing works; (ii) Consideration of location-dependent image sensitivities whereby images taken at certain places (e.g., pubs, hospitals) may impact privacy of some people in the images who do not want their occurrences or co-occurrences at those locations to be known; (iii) Need for a comprehensive privacy model that can determine the extent to which the privacy protection mechanism reduces practical privacy risks; (iv) Enforcing the privacy protection that conforms with different privacy needs of multiple people in the same image.

The objective of this project is to design an intelligent detector to assessing the integrity of digital visual content and automatically detect AI generated images or videos in the real time. The uniqueness of the proposed system is its ability of self-learning and self-evolving to capture synthetic content generated by new (currently unknown) AI models over time.

In this project, we aim to develop comprehensive message routing solution to provide the fundamental support of information management for the Internet of vehicles. We have designed approaches that deliver messages via a self-organized moving-zone-based architecture formed using pure vehicle-to-vehicle communication and integrates moving object modeling and indexing techniques to vehicle management. It can significantly reduce the communication overhead while providing higher delivery rates. For the successful roll out of IoV applications, we also need to ensure the identity and location privacy of the participating vehicles, for which we are working on a suite of security and privacy protection mechanisms.