I'm a PhD student at advised by Prof. Volkan Cevher.
Before that, I completed my MSc in Applied Mathematics at
advised by Prof. Pablo M. Olmos.
Even before that, I completed my BSc in Data Science and Engineering at
.
My research targets robustness in Natural Language Processing, where we desire Language Models to be safe against attacks, e.g., Jailbreaking or missclassification. More specifically, I'm interested in Adversarial Attacks, Adversarial Training and Neural Network Verification methods.