Andreas Müller
Since 2023, I have been a PhD student at the Ruhr University Bochum with generous support by the CASA cluster of excellence in Germany. My current work aims at improving the robustness of watermarking techniques for generative AI.
Previously, I was an internal auditor and data analyst at Volkswagen Group.
I completed my studies at Technical University of Braunschweig, specializing in IT security. During that time, I was also a co-founder and backend developer at AIPARK, which is now called Bliq, as well as a student assistant to my current PhD supervisor Erwin Quiring.
Recent News
- 02/2025: We received the notification that our paper Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models is accepted at CVPR 2025 in Nashville!
- 05/2024: Our paper The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision receives the best paper award at the Deep Learning Security and Privacy Workshop collocated with the S&P conference in San Francisco!
- 01/2024: I am spending a few months at the International Computer Science Institute (ICSI), affiliated with UC Berkeley, for a research visit.
Publications
Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models
A. Müller, D. Lukovnikov, J. Thietke, A. Fischer, and E. Quiring
Accepted at the Conference on Computer Vision and Pattern Recognition (CVPR), 2025
[html], [pdf]
The Impact of Uniform Inputs on Activation Sparsity and Energy-Latency Attacks in Computer Vision
A. Müller and E. Quiring
Deep Learning Security and Privacy Workshop (DLSP), 2024
[html], [pdf]
On the detection of image-scaling attacks in machine learning
E. Quiring, A. Müller, and K. Rieck
Annual Computer Security Applications Conference (ACSAC), 2023
[html], [pdf]