Dr. Alam joined Old Dominion 91¶ÌÊÓƵ in Fall 2024 and currently teaches AI/CYSE 421/521 (Generative AI in Cybersecurity) and CYSE 450 (Ethical Hacking and Penetration Testing). He served as an AI Teaching Fellow for the 2024-25 academic year and contributed to the development of the AI in Cyber Defense certificate at ODUGlobal.
Before joining ODU, he completed his Ph.D. in Computing and Information Systems at the 91¶ÌÊÓƵ of North Carolina at Charlotte in Summer 2024.
His current research focuses on developing AI-based adaptive and dynamic cybersecurity solutions to address complex cyber threats affecting critical infrastructures, Internet of Things (IoT), cyber-physical systems, and connected vehicles. He is an expert in Deep Reinforcement Learning and is currently investigating emerging cyber threats related to Generative AI, particularly Large Language Models (LLMs).
Ph.D. in Computing and Information Systems, 91¶ÌÊÓƵ of North Carolina at Charlotte, (2024)
Expertise
Research Interests
Critical Infrastructure Security, IoT Security, Cyber Physical Systems, AI Security, Connected Vehicle Security, Deep Reinforcement Learning
Articles
- Alam, M. and Wang, W. (2021). A comprehensive survey on data provenance: 91¶ÌÊÓƵ-of-the-art approaches and their deployments for IoT security enforcement. J. Comput. Secur. 29 (4) , pp. 423–446.
Conference Proceeding
- Alam, M., Das, L., Roy, S., Shetty, S. and Wang, W. (2025). RESTRAIN: Reinforcement Learning-Based Secure Framework for Trigger-Action IoT Environment (pp. 562-567) Dubai: 2025 International Wireless Communications and Mobile Computing (IWCMC).
- Wang, W., Alam, M. and Wang, Y. Privacy-Preserved and Incentivized Knowledge Sharing for Reinforced-Learning based IoT Platform Security Tokyo: 2025 8th Artificial Intelligence and Cloud Computing Conference (AICCC 2025).
- Alam, M., Mohaimenur Rahman, A B M and Wang, W. (2024). IoTHaven: An Online Defense System to Mitigate Remote Injection Attacks in Trigger-action IoT Platforms 2024 IEEE 30th International Symposium on Local and Metropolitan Area Networks (LANMAN) (pp. 15-20).
- Alam, M., Jahan, I. and Wang, W. (2024). IoTWarden: A Deep Reinforcement Learning Based Real-Time Defense System to Mitigate Trigger-Action IoT Attacks 2024 IEEE Wireless Communications and Networking Conference (WCNC) (pp. 1-6).
- Alam, M., Sajid, M. Sajidul Islam., Wang, W. and Wei, J. (2022). IoTMonitor: A Hidden Markov Model-based Security System to Identify Crucial Attack Nodes in Trigger-action IoT Platforms 2022 IEEE Wireless Communications and Networking Conference (WCNC) (pp. 1695-1700).
- 2024: AI Teaching Fellowship, Old Dominion 91¶ÌÊÓƵ