Soroush H. Zargarbashi
Doctoral Researcher @Cispa Helmholtz Center For Information Security
Signup · Get unlimited contacts
WORK HISTORY
Doctoral Researcher @Cispa Helmholtz Center For Information Security
DE
My works where focused on Trustworthy AI, specifically robustness, and quantification of the model’s uncertainty. My publications are- Conformal Prediction Sets for Graph Neural Networks (ICML 2023)- Robust Conformal Prediction with a Single Binary Certificate (ICLR2025)- Optimal Conformal Prediction under Epistemic Uncertainty (under review)- One Sample is Enough to Make Conformal Prediction Robust (under review)- EvA: Evolutionary Attacks on Graphs (under review)- Robust Yet Efficient Conformal Prediction Sets (ICML 2024)- Conformal Inductive Graph Neural Networks (ICLR 2024)
EDUCATION
University of Cologne
Doctor of Philosophy - PhD, Artificial Intelligence
Isfahan University of Technology
Bachelor’s Degree, Computer Software Engineering
CISPA Helmholtz Center for Information Security
Doctor of Philosophy - PhD, Trustworthy AI
University of Tehran
Master's degree, Computer Science / Artificial Intelligence
SKILLS
ABOUT SOROUSH H. ZARGARBASHI
I am a research assistant (PhD candidate) focusing on Trustworthy AI — robustness and uncertainty quantification. I work at CISPA Helmholtz Center for information security, as a PhD researcher. Previously I worked as intern at Apple (machine translation team).
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.