Monday, March 18, 2019
Keeping it safe: sharing data for research with quantifiable privacy
With an increasing number of people, devices, and sensors connected
with digital networks, individually generated data can be largely
collected and shared to advance research and benefit our society,
e.g., via collaborative biomedical studies and intelligent systems.
However, the data generated by individual users contain sensitive
information, the disclosure of which may incur serious privacy
concerns. In this talk, I will present my research to enable data
sharing for research purposes, while protecting individual privacy. My
work adopts differential privacy to protect individual participation
in the aggregated data, and proposes new quantifiable privacy notions
to protect person-specific sensitive information in the
individual-level data. I will show that my research provides rigorous,
provable privacy guarantees while retaining the utility of the data.
Towards the end, I will share my vision for privacy-preserving data
sharing and future research opportunities.
Dr. Liyue Fan is an Assistant Professor at SUNY Albany. Her research
is at the intersection of privacy and spatio-temporal data. She was
named one of the "Rising Stars in EECS" by MIT in 2015. Her current
research activities are supported by NSF and SUNY.