Hello and welcome to my website. My name is Franziska Boenisch and I’m a research associate at Fraunhofer AISEC (Applied and Integrated Security). At the same time, I am pursuing a PhD at Freie Universität Berlin.
My research interest lies at the intersection of Machine Learning (ML) and Data Privacy. Research has shown that trained ML models do not necessarily provide privacy for the underlying training datasets, as some attacks allow to restore (aspects of) the training data from the model parameters (e.g. model inversion attacks), or others allow to find out if a specific data point was included in the training dataset or not (membership inference attacks). Both can be harmful for the privacy of the individuals whose data is represented in the training dataset. Therefore, protecting privacy in ML models is a crucial task. I’m currently mainly researching in the area of Differential Privacy, a mathematical framework that provides formal privacy guarantees. Furthermore, my interest lies in the quantification of privacy loss and in the “translation” between a formal value of a privacy guarantees and real-world implications.
If you are interested in the activities of the PrivML research group I am coordinating, check out the tab Research Group.