Yigitcan Kaya
Scholar

Yigitcan Kaya

Google Scholar ID: tPiXuV0AAAAJ
Postdoc at UC Santa Barbara
Adversarial Machine LearningDeep LearningSecurity of Machine Learning
Citations & Impact
All-time
Citations
1,677
 
H-index
11
 
i10-index
11
 
Publications
20
 
Co-authors
16
list available
Resume (English only)
Academic Achievements
  • Papers published in IEEE S&P'26, NAACL'25, SaTML'25, ICLR'24; mentored 20+ undergraduate interns and junior researchers, leading to multiple top-venue publications and six PhD placements in leading programs.
Research Experience
  • Postdoctoral fellow at UCSB’s SecLab since October 2023, working with Giovanni Vigna and Chris Kruegel. Awarded the Intelligence Community (IC) Postdoctoral Research Fellowship for a proposal on developing AI-driven antifragile cyber defenses.
Education
  • PhD in Computer Science from the University of Maryland, College Park, advised by Prof. Tudor Dumitras.
Background
  • Research interests bridge AI for security and trustworthy AI; identified overthinking pathology in deep nets, developed realistic threat models against ML systems, advanced practical methods to improve fairness and privacy, and showed how distribution shift undermines deployed defenses.
Miscellany
  • Goes by Can, pronounced like 'John' (d͡ʒan).