Scholar
Felix Mächtle
Google Scholar ID: ldc10NsAAAAJ
Universität zu Lübeck
Citations & Impact
Citations
22
H-index
3
i10-index
1
Publications
6
Co-authors
2
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Recent Publications:
- - AutoStub: Genetic Programming-Based Stub Creation for Symbolic Execution, to be published at SBFT 2025.
- - OCEAN: Open-World Contrastive Authorship Identification, to be published at ACNS 2025.
- - Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts, arXiv preprint.
- - Trace Gadgets: Minimizing Code Context for Machine Learning-Based Vulnerability Prediction, arXiv preprint.
- - SWAT: Modular dynamic symbolic execution for java applications using dynamic instrumentation, International Conference on Tools and Algorithms for the Construction and Analysis of Systems.
Research Experience
- Current research focuses on using advanced natural language processing (NLP) to improve software security by identifying vulnerabilities, detecting malicious patterns, inferring authorship, or adding context-aware components to traditional analysis. Additionally, developing a multi-agent framework for automated program repair and investigating adversarial attacks on AI systems, such as prompt stealing in generative models like stable diffusion.
Education
- PhD Student: University of Lübeck; MSc in Computer Science: University of Lübeck; BSc in Computer Science: University of Lübeck.
Background
- Interests: Machine Learning, Adversarial Attacks, Code Analysis. About Me: I am a research assistant/PhD student at the Institute for IT-Security at the University of Lübeck, intrigued by the intersection of machine learning and code analysis.
Miscellany
- Please reach out to collaborate 😃
