ZI 2027, Zilverling, Faculty EEMCS,
University of Twente, Enschede,
I am a lecturer at University of Twente in the Semantics, Cybersecurity, and Services (SCS) group. My research focuses on explainable machine learning solutions for cyber security tasks such as incident response, malware analysis, and intrusion detection. My mission is to go beyond prediction probabilities, and extract semantically meaningful insights from ML models (especially under unsupervised settings with complex structured data).
Before joining UT, I was a PhD candidate/lecturer at TU Delft. During my PhD, I developed several explainable sequential machine learning tool-chains for automating cyber threat intelligence. These tool-chains extracted actionable insights from large volumes of cyber data in order to assist security analysts in understanding adversary behavior.
Next to research, I also spent 40% of my time developing and teaching cyber security lectures to BSc. (Computer Science and Engineering) students at TU Delft. I wrote about my teaching experience here, and the teaching material can be found under Cyber Security Lecture Series.
Outside of work, I love photography, painting, and traveling. I enjoy discussions about human psychology, devious behavior, cats, imposter syndrome, and… well… cats.
|I’m hiring a PhD student. See the project details here!
|Received the Henry Walker Travel Grant to attend SIGCSE’24 in Portland!
|I’m thrilled to join the SCS group @ Uni. of Twente as assistant professor starting Jan ‘24!
|Visiting Prof. Balzarotti at Eurecom to work on automated malware capability discovery via ML.
|My experience report on integrating cybersecurity across BSc courses is accepted at SIGCSE!
SIGCSECybersecurity as a Crosscutting Concept Across an Undergrad Computer
Science Curriculum: An Experience ReportIn Proceedings of the ACM SIGCSE Technical Symposium on Computer Science Education, 2024
EuroS&PSoK: Explainable Machine Learning for Computer Security ApplicationsIn IEEE European Symposium on Security and Privacy (Euro S&P), 2023
ECMLSECLEDS: Sequence Clustering in Evolving Data Streams via Multiple Medoids
and Medoid VotingIn Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), 2022
TDSCAlert-driven Attack Graph Generation using S-PDFAIn IEEE Transcations on Dependable and Secure Computing, 2021