I-Privacy Lab
The I-Privacy lab works to protect privacy for everyone who is surfing the Internet and entering the era of Internet of Things. We work on a variety of cutting-edge research topics such as mobile app security, location privacy, image privacy protection on social network, ransomware detection and defense, attacking and defending artificial intelligence, security and privacy issues in autonomous cars, security and privacy issues in big data processing. We have a group of talented graduate students and we offer different types of scholarship such as the following NSF SFS program.
-
Broad-Spectrum Facial Image Protection with Provable Privacy Guarantees (Funded by NSF)
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.
-
Detection of Images and Videos Created by Artificial
Intelligence (Funded by NSF)
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.
-
Information Management and Security Protection for Internet of Vehicles
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.
Post Doctoral Research Associate: Ali Allami, expert on secure multi-party computation
- Ke L. (PhD) , work on “voice authentication attacks and defense”.
- Cameron B. (PhD), work on “AI generated voice detection”.
- Ian M. (PhD), work on “AI attack and defense”.
- Jay B. (PhD), work on “AI generated image detection”.
- Alex E. (PhD), work on “Privacy protection in human behavior sensing and distributed environments”.
Former Students (13 PhD and 7 MS thesis students have already graduated from our lab. )