Machine Learning for Privacy, Privacy for Machine Learning

Back to the program

 

Title: Machine Learning for Privacy, Privacy for Machine Learning

Speaker: Mathias Humbert, Cyber-Defence Campus, armasuisse S+T, Switzerland

Date: September 09, Wednesday
Time: 12:00 – 14:00 (Israel, UTC+03:00)
10:00 – 12:00 (UK, UTC+01:00)
05:00 – 07:00 (EDT, UTC-04:00)
19:00 – 21:00 (AEST, UTC+10:00)

Abstract: The fuel of the ongoing artificial intelligence revolution is data, which is key for the development of robust machine-learning models. However, the increasingly data-driven economy and science also create new risks toward the privacy of data contributors. In this talk, I will first show how machine learning can help evaluate privacy risks in biomedical datasets, with a focus on three key attacks against privacy. Second, I will present tailored defense mechanisms for preventing such attacks and enhancing privacy in machine learning while preserving utility and efficiency.

Bio: Mathias Humbert is a scientific project manager at the newly created Cyber-Defence Campus (Switzerland). Prior to this, he was a senior data scientist at the Swiss Data Science Center (ETH Zurich, EPFL) and a post-doctoral researcher at the Center for IT-Security, Privacy, and Accountability (CISPA) in Saarbrücken, Germany. He completed his Ph.D. thesis on privacy protection in early 2015 in the School of Computer and Communication Sciences at EPFL, after M.Sc. (2009) and B.Sc. (2007) studies at EPFL and UC Berkeley. He is a recipient of the NDSS 2019 distinguished paper award.