Talk: Ownership protection in Machine Learning: How to protect your neural network?
Outsourcing the complex Machine Learning (ML) models to cloud services witnessed a great growth over the past years as the costs of producing and maintaining ML systems can be decreased this way. However, the owners/creators of these models, by sharing them online, face the threat of model stealing and other types of unauthorised usages.
In this talk I would like to motivate the model watermarking as one of the ownership protection methods that allows the owners of ML models, in most of the cases deep neural networks (DNNs), to embed their signature into the models and this way trace the unauthorised usage. Two main requirements for watermarking techniques are (i) robustness, i.e., the mark should not be easily removable by third parties, and (ii) utility preservation, i.e., the mark should not introduce significant degradations to model performance. We will discuss the challenges related to these main requirements and applicability of the state-of-the-art techniques in the real-life scenarios.
17:40 Expert Talk
19:30 Community Topics
Speaker & Details
- Tanja Šarčević, SBA Research
- Talk language: English
- Event on site at SBA Research
About the Speaker
Tanja Šarčević is a researcher in Machine Learning and Data Management team in SBA Research and currently working towards her PhD in computer science at TU Wien under supervision of Andreas Rauber. Her main research interests are privacy and security issues in data sharing and machine learning processes, in particular, data anonymization, privacy-preserving computation and ownership protection. Tanja received her bachelor’s degree in Computer Science from the Faculty of Electrical Engineering and Computing in Zagreb in 2016, and a master’s degree in Logic and Computation at TU Wien in 2019.
Please register via our Meetup Group Women in Privacy & Security Vienna
The MeetUp is free for all women+ & women+ only.
Please note that this is an event for women-only event that intends an inclusive definition of women. We are welcoming and respectful of women, including amab transgender persons and those that are nonbinary, gender non-conforming, and any others who identify as a woman in a way that is significant to them.
About the event series
This meetup group is founded by female experts from SBA Research, TU Wien and University of Vienna (Members of VISP Vienna Security Privacy Research Cluster Vienna).