Portrait

Prof. Dr. Konrad Rieck

Room
FR 758 (see 7½th floor)
Address
BIFOLD & TU Berlin
Machine Learning and Security
Franklinstraße 28-29
10587 Berlin, Germany

About me

I am a Professor of Computer Science at TU Berlin, where I head the Chair of Machine Learning and Security within the Berlin Institute for the Foundations of Learning and Data. Previously, I have been working at TU Braunschweig, University of Göttingen, and Fraunhofer Institute FIRST. Additionally, I have been a Guest Professor at TU Wien in 2024.

My research interests revolve around computer security and machine learning. My group is developing novel methods for detecting computer attacks, analyzing malicious software and discovering security vulnerabilities. Moreover, we explore the security and privacy of learning algorithms. I am also interested in efficient algorithms for analyzing structured data, such as strings, trees, and graphs.

My Erdős number is 3 (Müller → Jagota → Erdős) and my Bacon number is ∞. I am a very distant academic relative of Carl Friedrich Gauß (see here), although this doesn't help when solving math problems.

Selected Publications

LLM-based Vulnerability Discovery through the Lens of Code Metrics.
Felix Weissberg, Lukas Pirch, Erik Imgrund, Jonas Möller, Thorsten Eisenhofer and Konrad Rieck.
48th IEEE/ACM International Conference on Software Engineering (ICSE), 2026. (to appear)

PDF Code

Manipulating Feature Visualizations with Gradient Slingshots.
Dilyara Bareeva, Marina M.-C. Höhne, Alexander Warnecke, Lukas Pirch, Klaus-Robert Müller, Konrad Rieck, Sebastian Lapuschkin and Kirill Bykov.
Advances in Neural Information Processing Systems 39 (NeurIPS), 2025. (to appear)

Adversarial Observations in Weather Forecasting.
Erik Imgrund, Thorsten Eisenhofer and Konrad Rieck.
32nd ACM Conference on Computer and Communications Security (CCS), 2025.
Distinguished Paper Award

PDF Code

Seeing through: Analyzing and Attacking Virtual Backgrounds in Video Calls.
Felix Weißberg, Jan-Malte Hilgefort, Steve Grogorick, Daniel Arp, Thorsten Eisenhofer, Martin Eisemann and Konrad Rieck.
34th USENIX Security Symposium, 2025.

PDF Code Data

Adversarial Inputs for Linear Algebra Backends.
Jonas Möller, Lukas Pirch, Felix Weissberg, Sebastian Baunsgaard, Thorsten Eisenhofer and Konrad Rieck.
42nd International Conference on Machine Learning (ICML), 2025.

PDF Code

See all publications.

Awards

  • CCS Distinguished Paper Award 2025
  • USENIX Security Distinguished Paper Award 2024
  • IEEE S&P Test-of-Time Award 2024
  • USENIX Security Distinguished Paper Award 2022
  • ERC Consolidator Grant 2021
  • AISEC Best Paper Award 2021
  • Winner of Microsoft MLSEC competition 2020
  • LehrLeo: Best Lecture at TU Braunschweig 2019
  • LehrLeo: Best Lab Course at TU Braunschweig 2019
  • German Prize for IT-Security 2016 (2nd Place)
  • DIMVA Best Paper Award 2016
  • Google Faculty Research Award 2014
  • ACSAC Outstanding Paper Award 2012
  • CAST/GI Dissertation Award IT-Security 2010

Academic Memberships

Conference and Workshop Organization

Reviewing Awards

  • ACSAC Distinguised Reviewer Award 2024
  • EuroS&P Distinguished Reviewer Award 2024
  • SATML Notable Reviewer Award 2024
  • ACSAC Top Reviewer Award 2023
  • RAID Noteworthy Reviewer Award 2023
  • USENIX Security Noteworthy Reviewer Award 2023
  • CCS Top Reviewer Award 2022
  • DLS Outstanding Reviewer Award 2018
  • RAID Outstanding Reviewer Award 2015

Recent PC Memberships

Review and Email Activity

For fun, I am tracking my reviewing and email activity. Here are two plots showing my reviewing activity over the last years. As you can see, I am writing a lot of reviews per year. Most of the time, this is fun.

Statistics of reviewing
Statistics of review length

Similarly, here are two plots showing the number of incoming and outgoing emails on my university account over the last two weeks. The average and standard deviation are calculated over several years (see week number in legend).

Statistics of incoming emails
Statistics of outgoing emails

Whenever Possible

I am a member of "Verband der krawattenlosen Wissensträger" (VDKW)