On December 21, 2023, Franziska Boenisch of CISPA Helmholtz Center for Information Security talked about „Machine Learning with Individualized Privacy Guarantees” during research seminar at IDEAS NCBR. This was the second part of a double research seminar with Adam Dziedzic (see here: • ADAM DZIEDZIC: Private... )
Abstract:
When applying machine learning (ML) in sensitive domains, we have to ensure privacy protection to avoid the leakage of the private training data from the model. The standard approach to implement privacy is to integrate differential privacy (DP) into the training procedure. For training a model with DP, one sets a privacy budget which represents a maximal privacy violation that any individual is willing to face by contributing their data to the training set. We argue that this approach is limited because different individuals may have different privacy expectations. Thus, setting a uniform privacy budget across all points may be overly conservative for some individuals or, conversely, not sufficiently protective for others. Building on the standard algorithms for privacy-preserving ML, we propose Individualized DP (IDP) algorithms for machine learning. Our algorithms do not only allow to respect individuals’ privacy preferences, but also enable to leverage training data more efficiently which results in better ML model utility and thereby supports a broader practical deployment of privacy-preserving ML in sensitive domains.
Bio:
Franziska Boenisch is a tenure-track faculty at @cispa2555 CISPA Helmholtz Center for Information Security where she co-leads the SprintML lab. Before, she was a Postdoctoral Fellow at the University of Toronto and Vector Institute advised by Prof. Nicolas Papernot. Her current research centers around private and trustworthy machine learning. Franziska obtained her Ph.D. at the Computer Science Department at Freie University Berlin, where she pioneered the notion of individualized privacy in machine learning. During her Ph.D., Franziska was a research associate at the Fraunhofer Institute for Applied and Integrated Security (AISEC), Germany. She received a Fraunhofer TALENTA grant for outstanding female early career researchers and the German Industrial Research Foundation prize for her research on machine learning privacy.
#ppml #llms #machinelearning #ideasncbr
17 сен 2024
