I am currently a Postdoctoral Researcher at Trustworthy Human Language Technologies (TrustHLT), Ruhr University Bochum (RUB), working with my postdoc advisor, Prof. Dr. Ivan Habernal. My research primarily focuses on attacks against Large Language Models (LLMs), including prompt injection, membership inference, model inversion, gradient reconstruction, model extraction, backdoor attacks, and adversarial evaluation of AI systems.

Previously, I completed my Dr. rer. nat. at Software Innovation Campus Paderborn (SICP), Paderborn University, under the supervision of Prof. Dr. Eyke Hüllermeier, where my research focused on advanced machine learning methods for information leakage detection in cryptographic systems. During my doctoral studies, I developed machine learning and information-theoretic methods for side-channel analysis, automated attack generation using AutoML and Neural Architecture Search, and security evaluation of cryptographic implementations. My dissertation was reviewed by Prof. Dr. Eyke Hüllermeier and Prof. Dr. Juraj Somorovsky. Prof. Dr. Juraj Somorovsky provided guidance in cryptography and machine-learning approaches to security analysis, alongside detailed review of my dissertation.

I received my Bachelor's degree in Computer Engineering from NSIT, Delhi University, now known as Netaji Subhas University of Technology (NSUT). During my bachelor’s studies, I investigated the performance of broadcasting algorithms for mobile ad hoc networks under the supervision of Dr. Bijendra Kumar. I also served as joint secretary of the IEEE Computer Society chapter at NSIT and helped organize technical and cultural events.

Before pursuing my PhD, I worked as a Software Engineer at Samsung Research Institute-Noida (SRI-Noida), contributing to Android framework development and mobile software engineering. This industrial experience continues to influence my research by motivating practical, secure, and deployable AI systems.