My research focuses on the intersection of Artificial Intelligence and Security, with a current emphasis on Large Language Models and Membership Inference Attacks.
I am a PhD student in the Department of Information and Systems Engineering at Concordia University, Montréal. My research sits at the intersection of artificial intelligence and cybersecurity — a space growing rapidly in both scope and significance.
My current work investigates Membership Inference Attacks on Large Language Models (LLMs) — exploring how models may inadvertently reveal information about their training data, with implications for data privacy, model auditing, and responsible AI deployment.
Prior to joining Concordia, I completed both my undergraduate and graduate studies at Nile University, Egypt, where I built a strong foundation in computer science and information security.
Investigating the vulnerability of LLMs to membership inference — determining whether a specific data record was used during model training. This work has direct implications for training data privacy and regulatory compliance around AI systems.
Broader research into adversarial threats against AI systems, including prompt injection, model extraction, and data poisoning — examining both attack surfaces and defensive strategies.