"There is no one who goes out of his house to seek knowledge, but the angels lower their wings in approval of his action." 

- The Prophet ﷺ 

Welcome to My Webpage!

I'm a second-year PhD student in the College of Information Sciences and Technology (IST) at Pennsylvania State University, currently working in the Penn State Cyber Security Lab under Professor Peng Liu, Raymond G. Tronzo, M.D., Professor of Cybersecurity. Before this, I obtained my bachelor's degree from the Department of Computer Science and Engineering (CSE) at Bangladesh University of Engineering and Technology (BUET) in 2023. After graduation, I served as a full-time Lecturer at United International University (UIU), Bangladesh.

Research Interest:

My research focuses on advancing "cybersecurity and privacy" by securing cyber-physical systems, with an emphasis on detecting, reasoning about, and mitigating malicious behavior in complex systems.

• Cyber-Physical System Security --- Designing a multi-agent LLM framework to enhance Bayesian Network reasoning, improve scalability, and automate knowledge extraction. Previously developed methods to distinguish faults and cyberattacks in DER systems using taint-style dependency graphs with node pruning and pattern matching.

  • LLM-based multi-agent systems: Developed AgentBN, an LLM-driven multi-agent framework for Bayesian network refinement featuring agent orchestration, structured prompting, deterministic evaluation pipelines, iterative self-correction, and output validation for trustworthy AI. Leveraged probabilistic inference and deterministic validation to evaluate Bayesian network refinements through confidence analysis and candidate selection. (GitHub).

  • Bayesian reasoning for DER security: Developed Bayesian-network reasoning that integrates domain-specific causal knowledge with probabilistic inference to automate cyber-physical root-cause analysis while handling real-world uncertainty (PESGM'26).

  • Integrated cyber-physical analysis: Developed a semi-automatic framework (a.k.a., PVOTA) that combines novel taint analysis with domain-specific patterns to bridge cyber logs and physical measurements, enabling fault and cyberattack differentiation in DER systems (distributed energy resources) systems (arXiv).

• IoT Network Traffic Analysis--- Explored security and privacy in Industrial and Smart Home IoT networks, including detecting smart home device activities from encrypted traffic, uncovering dual-purpose MQTT protocol traffic-based adversarial attacks in industrial IoT systems, and conducting literature review on metaheuristics- and ML-based NIDSs (network intrusion detection systems) in IoT. (TDSC: GitHub, SWEVO, IoT, ..., CMC: GitHub)