Lukas Struppek
Scholar

Lukas Struppek

Google Scholar ID: tU8K5qsAAAAJ
Senior Research Scientist @ German Research Center for AI (DFKI)
Trustworthy Generative AI
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,023
 
H-index
13
 
i10-index
15
 
Publications
20
 
Co-authors
0
 
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
AI Security Leaderboard: Methodology, Results and Minimal Standard
2026
Cited
0
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill Attacks
2026
Cited
0
Focused Chain-of-Thought: Efficient LLM Reasoning via Structured Input Information
2025
Cited
0
Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed
2025
Cited
0
Resume
Academic Achievements
  • 1. Recognized as a top reviewer at NeurIPS 2025.
  • 2. Received the IANUS Award for outstanding research promoting peace and security responsibility in the natural and technical sciences.
  • 3. Published paper: 'Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models'.
Research Experience
  • Currently a research scientist at FAR.AI, working on robustness and safety of frontier large language models. Previously, a senior research scientist at the German Research Center for Artificial Intelligence (DFKI).
Education
  • PhD (Dr. rer.nat) from the Artificial Intelligence and Machine Learning Lab at Technical University of Darmstadt; M.Sc. and B.Sc. in Industrial Engineering and Management from Karlsruhe Institute of Technology (KIT).
Background
  • Passionate about building trustworthy AI systems. Research focuses on generative and multimodal AI, addressing security, privacy, and safety challenges.
Miscellany
  • Always happy to collaborate and discuss novel research ideas.