Dren Fazlija
Scholar

Dren Fazlija

Google Scholar ID: lWQHyMoAAAAJ
Ph.D. Student, L3S Research Center
LLM SafetyAdversarial Machine LearningAlignment
Citations & Impact
All-time
Citations
31
 
H-index
2
 
i10-index
1
 
Publications
8
 
Co-authors
15
list available
Resume (English only)
Academic Achievements
  • Involved in four grant proposals, three led by our research center, one co-conceived by me; Supervision of ten students ranging from seminars to theses; Involved in multiple transfer projects to support local organizations and enterprises; Development of larger prototype systems, predominantly for the local education sector.
Research Experience
  • Research Associate: L3S Research Center, Leibniz University Hannover, Germany, July 2022 - Present, Research in the field of robust AI; AI Expert: European Digital Innovation Hub for AI and Cybersecurity (DAISEC), Germany, April 2025 - Present, Involved as an AI Expert in European Transfer Project; Project Coordinator: 'Zukunftslabor Gesellschaft und Arbeit’, Zentrum für digitale Innovationen Niedersachsen, Germany, July 2022 - April 2025, Managed & coordinated over 20 researchers across 8 research institutes in Lower Saxony.
Education
  • Doctor (Dr. rer. nat.) in Computer Science: July 2022 - Present, Topic: Secure Foundation Models; Master (M. Sc.) in Computer Science: October 2019 - January 2022, Grade: 1.6 (German grading system), 3.4 GPA, Focus on multifaceted research area of AI.
Background
  • Research Interests: Adversarial Machine Learning, particularly adversarial examples, LLM security, and model stealing. Professional Field: Artificial Intelligence.
Miscellany
  • Interests include Basketball, Football, Tennis, Day Trips, Video Games, and wasting hours on random YouTube videos. Languages: German (Native Speaker), English (Professional working proficiency), Albanian (Enough for playground insults).