Masterarbeit: Robustheit von Autorschaftsverifikation gegenĂĽber Adversarial Obfuscation
Fraunhofer-GesellschaftDarmstadt, Hesse, Germany
Posted December 23, 2025
Internship
About the Company
The Fraunhofer Society is one of the world's leading organizations for application-oriented research, with a focus on future-relevant key technologies and the exploitation of results in economy and industry.
Job Description
Master Thesis: Robustness of Authorship Verification against Adversarial Obfuscation. The goal of this work is to investigate various attacks on stylization and develop an AV system that is as robust as possible against them.
Requirements
- Knowledge in the field of Machine Learning, ideally in the field of NLP and Transformer models.
- Good Python knowledge, preferably experience with PyTorch or HuggingFace.
- Scientific interest in robustness, security, and evaluation metrics in AI systems.
- Motivation to deal with adversarial attacks and modern AV approaches.
Benefits
- Self-organized working hours
- Insights into the intersection of academic research and industrial application
