Portrait

Alexander Warnecke

Room
TEL 805
Address
FG Machine Learning and Security
Technische Universität Berlin
Ernst-Reuter-Platz 7
10587 Berlin, Germany

About me

I am a PhD student at Technische Universität Berlin. I am part of the Chair of Machine Learning and Security within the Berlin Institute for the Foundations of Learning and Data (BIFOLD). My research revolves around applications of Machine Learning for Computer Security aswell as privacy and security of modern Machine Learning Models.

Publications

Evil from Within: Machine Learning Backdoors Through Dormant Hardware Trojans.
Alexander Warnecke, Julian Speith, Jan-Niklas Möller, Konrad Rieck and Christof Paar.
Proc. of the 40th Annual Computer Security Applications Conference (ACSAC), 2024. (to appear)

Pitfalls in Machine Learning for Computer Security.
Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro and Konrad Rieck.
Communications of the ACM, 67, (11), 2024.

Link

Security Viewpoints on Explainable Machine Learning.
Alexander Warnecke.
PhD thesis, Technische Universität Berlin, 2024.

PDF

Manipulating Feature Visualizations with Gradient Slingshots.
Dilyara Bareeva, Marina Höhne, Alexander Warnecke, Lukas Pirch, Klaus-Robert Müller, Konrad Rieck and Kirill Bykov.
Technical report, arXiv:2401.06122, 2024.

Link

Lessons Learned on Machine Learning for Computer Security.
Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro and Konrad Rieck.
IEEE Security & Privacy, 21, (4), 2023.

PDF Link

Evil from Within: Machine Learning Backdoor through Hardware Trojans.
Alexander Warnecke, Julian Speith, Jan-Niklas Möller, Konrad Rieck and Christof Paar.
Technical report, arXiv:2304.08411, 2023.

PDF Link

Machine Unlearning of Features and Labels.
Alexander Warnecke, Lukas Pirch, Christian Wressnegger and Konrad Rieck.
Proc. of the 30th Network and Distributed System Security Symposium (NDSS), 2023.

PDF Code

Dos and Don'ts of Machine Learning in Computer Security.
Daniel Arp, Erwin Quiring, Feargus Pendlebury, Alexander Warnecke, Fabio Pierazzi, Christian Wressnegger, Lorenzo Cavallaro and Konrad Rieck.
Proc. of the 31st USENIX Security Symposium, 2022.
Distinguished Paper Award

PDF Project

Explaining Graph Neural Networks for Vulnerability Discovery.
Tom Ganz, Martin Härterich, Alexander Warnecke and Konrad Rieck.
Proc. of the 14th ACM Workshop on Artificial Intelligence and Security (AISEC), 2021.
Best Paper Award

PDF

TagVet: Vetting Malware Tags using Explainable Machine Learning.
Lukas Pirch, Alexander Warnecke, Christian Wressnegger and Konrad Rieck.
Proc. of the 14th ACM European Workshop on Systems Security (EuroSec), 2021.

PDF

Evaluating Explanation Methods for Deep Learning in Security.
Alexander Warnecke, Daniel Arp, Christian Wressnegger and Konrad Rieck.
Proc. of the 5th IEEE European Symposium on Security and Privacy (EuroS&P), 2020.

PDF Project Code