Balance and reinforcement: privacy and fairness in high intelligence models

Project Member(s): Yu, S., Wang, S.

Funding or Partner Organisation: Australian Research Council (ARC Discovery Projects)
Australian Research Council (ARC Discovery Projects)

Start year: 2024

Summary: The goal of this project is to design a series of new privacy and fairness analysis strategies for current intelligence technologies to reduce the public’s privacy and model discrimination concerns. Advancement of these strategies takes advantages of the mutual reinforcement effect of privacy and fairness in intelligence models. The novel theory and practical will improve the model privacy and fairness in real-world situation. The new privacy and fairness strategies will create a distinct competitive edge for Australia in the field of deep learning. Medium-term, these solutions could be used by any organisations that relies on deep learning algorithms for tasks such as national decision-making; banking and securities; trade and customs; autonomous driving, and many others. Further, the cutting-edge privacy and fairness strategies integrated into the architecture will ensure Australians and their AI algorithms remain secure in a world of ongoing cybersecurity threats.

FOR Codes: Cybersecurity, Data and information privacy, Data security and protection

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.