Mahbub Alam

Howdy!

I am a Ph.D. student in Computer Science at Texas A&M University, working under the supervision of Prof. Nitesh Saxena at the SPIES Lab.

I began my Ph.D. in Fall 2024, and my research broadly focuses on the security of modern AI systems, particularly large language models. My work aims to understand how these systems fail, how they can be exploited, and how to systematically improve their robustness.

To this end, I take a two-fold approach. First, I develop LLM-assisted reasoning frameworks to analyze and synthesize security research at scale, enabling the discovery of gaps, limitations, and emerging threats. Second, I design techniques to identify vulnerabilities in AI systems, with a focus on adversarial behaviors and failure discovery.

My work has appeared in top-tier security venues, including USENIX Security, IEEE SecDev, and eCrime, with additional papers currently under review.

Prior to my Ph.D., I worked as a Site Reliability Engineer, focusing on cloud infrastructure, reliability, and security. This experience continues to inform my research with a practical, systems-oriented perspective.

News

• September, 2025: Our paper “Infrastructure Patterns in Toll Scam Domains: A Comprehensive Analysis of Cybercriminal Registration and Hosting Strategies” will appear in APWG eCrime 2025.

• August, 2024: Our paper “iConPAL: LLM-guided Policy Authoring Assistant for Configuring IoT Defenses” will appear in IEEE SecDev 2024.

• August, 2024: Began my Ph.D. in Computer Science at Texas A&M University, focusing on AI Safety & Security and AI for Cybersecurity, under the guidance of Dr. Nitesh Saxena.

• September, 2017: Graduated with a Bachelor’s degree from the Department of Computer Science and Engineering (CSE), BUET.