Lunch Talk: Felix Weißberg "ML for Security: A Journey Through Software Layers"

During this Lunch Talk, Felix Weißberg from BIFOLD will talk about " ML for Security: A Journey Through Software Layers". He introduces how effectively security vulnerabilities can be detected across software layers — in both custom source code and proprietary dependencies while critically examining state-of-the-art and machine learning-driven approaches. Finally, he presents a picture of significant potential tempered by a sobering reality.

Abstract: Whether you are improving medical processes, managing large volumes of data, or observing the earth from space, you rely on domain-specific software stacks, and in most cases you develop your own software. In either situation, you would likely prefer that this software is not riddled with security vulnerabilities. So how can you assess whether it is?
In this talk, Felix Weißberg will explore the different layers of software and examine how effectively vulnerabilities can be detected, both in custom source code and in proprietary libraries on which researchers depend. To this end, he will draw on state-of-the-art approaches, apply machine learning-driven enhancements, and take a critical look at the usage of machine learning in this domain. Finally, Felix will present a mixed picture, with significant potential on the one hand and a generally sobering reality on the other.

The BIFOLD Lunch Talk series gives BIFOLD members and external partners the opportunity to engage in dialogue about their research in Machine Learning and Big Data. Each Lunch Talk offers BIFOLD members, fellows and colleagues from other research institutes the chance to present their research and to network with each other.
The Lunch Talk takes place at BIFOLD and online. For further information on the Lunch Talks and registration, contact Dr. Laura Wollenweber via email.