Presentation:
Privacy-preserving collaborative training of kernel-based Machine Learning methods
Machine Learning has proven its success on various problems from many different domains. Even though the amount varies between the Machine Learning algorithms, they require sufficient amounts of data to recognize the patterns in the data. One of the easiest ways to meet this need of the Machine Learning algorithms is to use multiple sources generating the same type of data. One can easily satisfy the desire of the Machine Learning algorithms for data using these sources. However, this can cause a privacy leakage. The data generated by these sources may contain sensitive information that can be used for undesirable purposes. Therefore, although the Machine Learning algorithms demand data, the sources may not be willing or even allowed to share their data. A similar dilemma occurs when the data owner wants to extract useful information from the data by using Machine Learning algorithms but it does not have enough computational power or knowledge. In this case, the data source may want to outsource this task to external parties that offer Machine Learning algorithms as a service. Similarly, in this case, the sensitive information in the data can be the decisive factor for the owner not to choose outsourcing, which then ends up with non-utilized data for the owner. In this talk, I will present our works addressing the privacy preserving training of kernel-based Machine Learning algorithms with different cryptographic techniques, and talk about the demonstrated efficiency and applicability of our works on the personalized treatment prediction system of HIV infected patients.
Bio
Mete Akgün is a computer scientist and security researcher at the University of Tübingen where he leads the Medical Data Privacy and Privacy-preserving ML (MDPPML) group. Before joining the University of Tübingen as a group leader, he worked as a senior researcher in the Center of Research for Advanced Technologies of Informatics and Information Security (TUBITAK BILGEM), Kocaeli, Turkey. He received his PhD degree in Computer Engineering from Bogazici University, Turkey in 2016. His research interests are in the area of applied cryptography, data privacy, security protocols, and machine learning.
Back to the Summer School 2022 overview