Linking Sensitive Data: Approaches and Vulnerabilities
With much data about people being highly sensitive (private or confidential), linking personal data from multiple organisations can result in privacy concerns and the risks of data breaches. What is required are techniques that allow the linking of sensitive data across diverse organisations to facilitate data analytics and Machine Learning, while at the same time preserving the privacy of the individuals whose records are being linked. data in privacy-preserving ways. We cover application examples and key technologies to encode sensitive data, and then we discuss one topic in detail: what makes sensitive data vulnerable. We present a novel framework to assess the vulnerabilities that an adversary can potentially exploit in order to reidentify sensitive plaintext values from encoded data. We conclude our talk with a discussion of challenges and future research directions when dealing with sensitive data.
Joint presentation with: Prof. Peter Christen
Information about the biography of Dr. Anushka Vidanage can be found here.
Back to the Summer School 2022 overview