Mabon Ninan

Mabon Ninan

he/him/his

PhD Student at Texas A&M University@[Botacin's Lab]

CV

Research profile: machine learning and security, with a focus on side-channel analysis, malware detection, explainable AI, and student mentorship.

Education

  • Ph.D. in Computer Science, Texas A&M University, Aug. 2024 – Present
    • Advisor: Dr. Marcus Botacin
    • Thesis: Algorithms and Advanced Machine Learning for Cybersecurity
    • Committee: Dr. James Caverlee, Dr. Nitesh Saxena, Dr. Eman Hammad
  • B.S. in Computer Engineering, University of Cincinnati, Aug. 2020 – Apr. 2024
    • Summa Cum Laude (3.953/4.00)
    • Advisor: Dr. Boyang Wang
    • Thesis: Domain Adaptation for Deep Learning Models and Tiny Neural Networks

Awards & Honors

  • Best Student Paper, IEEE HOST 2024
  • Undergraduate Research Fellowship, University of Cincinnati, 2022, 2023, 2024

Research Experience

  • Texas A&M University, Research Assistant, Aug. 2024 – Present
    • Designing interpretable and robust malware detection methods for real-world deployment.
    • Developing agentic and LLM-assisted security systems for evolving cyber threats.
    • Investigating explainability and uncertainty in security models.
  • Cincinnati Children’s Hospital Medical Center, Research Scientist, May 2024 – Aug. 2024
    • Built multimodal systems for pediatric chest X-ray report generation and evaluation.
    • Developed foundation models for CXR imaging and interpretable clinical AI.
    • Evaluated commercial NLP services and medical labelers on pediatric datasets.
  • University of Cincinnati, Research Assistant, Jul. 2022 – Aug. 2024
    • Developed pruning methods that reduced model size by up to 98% for embedded deployment.
    • Explored domain adaptation, tiny neural networks, and side-channel trace analysis.
    • Supervised undergraduate students on a large public EM side-channel dataset.

Publications

  • Mabon Ninan, Ryan Evans, Logan Reichling, Nirnimesh Ghose, Boyang Wang. “TinyRadio: Tiny Neural Networks for Fingerprinting Radio Frequency Signals.” IEEE National Aerospace and Electronics Conference (NAECON), 2025. DOI: 10.1109/NAECON65708.2025.11235437.
  • Logan Reichling, Ryan Evans, Mabon Ninan, Phuc Mai, Boyang Wang, Yunsi Fei, John Emmert. “MicroPower: Micro Neural Networks for Side-Channel Attacks.” In 2025 IEEE International Symposium on Hardware Oriented Security and Trust (HOST), 2025. DOI: 10.1109/HOST64725.2025.11050048.
  • Mabon Ninan, Evan Nimmo, Shane Reilly, Channing Smith, Wenhai Sun, Boyang Wang, John M. Emmert. “A Second Look at the Portability of Deep Learning Side-Channel Attacks over EM Traces.” In RAID ’24: The 27th International Symposium on Research in Attacks, Intrusions and Defenses, pp. 630–643. ACM, 2024. DOI: 10.1145/3678890.3678900.
  • Haipeng Li, Mabon Ninan, Boyang Wang, John M. Emmert. “TinyPower: Side-Channel Attacks with Tiny Neural Networks.” In 2024 IEEE International Symposium on Hardware Oriented Security and Trust (HOST), pp. 320–331. IEEE, 2024. DOI: 10.1109/HOST55342.2024.10545382.
  • Andrew Kosikowski, Daniel Cho, Mabon Ninan, Anca Ralescu, Boyang Wang. “EvilELF: Evasion Attacks on Deep-Learning Malware Detection over ELF Files.” In 2023 International Conference on Machine Learning and Applications (ICMLA), pp. 1702–1709. IEEE, 2023. DOI: 10.1109/ICMLA58977.2023.00258.
  • Chenggang Wang, Mabon Ninan, Shane Reilly, Joel Ward, William Hawkins, Boyang Wang, John M. Emmert. “Portability of Deep-Learning Side-Channel Attacks against Software Discrepancies.” In Proceedings of the 16th ACM Conference on Security and Privacy in Wireless and Mobile Networks (WiSec ’23), pp. 227–238. ACM, 2023. DOI: 10.1145/3558482.3590177.
  • Logan Reichling, Mabon Ninan, Boyang Wang, John M. Emmert. “Deep Learning Side-Channel Attacks: Challenges and Opportunities.” Book chapter in Advancements in Hardware Design and Trust, 2026.
  • Shruti Hegde, Mabon Ninan, Jonathan R. Dillman, Shireen Hayatghaib, Elanchezhian Somasundaram. “Evaluating Clinical NLP Services for Chest Radiograph Report Labeling: A Comparative Study on an Independent Pediatric Dataset.” Journal of Imaging Informatics in Medicine, June 2026.
  • Shruti Hegde, Mabon Ninan, Jonathan R. Dillman, Shireen Hayatghaibi, Lynn Babcock, Elanchezhian Somasundaram. “Can Modern NLP Systems Reliably Annotate Chest Radiography Exams? A Pre-Purchase Evaluation and Comparative Study of Solutions from AWS, Google, Azure, John Snow Labs, and Open-Source Models on an Independent Pediatric Dataset.” DOI: 10.21203/rs.3.rs-6772394/v1.

Talks

  • CSCE Graduate Seminar, Texas A&M University, Feb. 2026
  • AI for Cybersecurity Research, Texas A&M University, Feb. 2025
  • RAID 2024, Padua, Italy, Sep. 2024
  • IEEE HOST 2024, Washington, D.C., May 2024
  • WiSec 2023, Guildford, United Kingdom, May 2023

Academic Service

  • PC Member, RAID 2026
  • PC Member, DSN 2026
  • PC Member, RAID 2025
  • Reviewer, Computers & Security (COSE), 2026
  • PC Member, The 41st ACM/SIGAPP Symposium on Applied Computing
  • Artifact Evaluator, CCS 2025

Technical Skills

  • Languages: Python, C/C++, Assembly, SQL
  • Machine Learning: PyTorch, TensorFlow, Transformers, Scikit-learn, Computer Vision, NLP
  • Security & Tools: Malware Analysis, Reverse Engineering (ELF), AWS, Google Cloud, Azure, Docker, Git, Linux

Co-Advised Students

Selected undergraduate and REU mentees

Mentoring

  • Co-advised undergraduate researchers on side-channel security, malware analysis, and machine learning projects.
  • Mentored students who have gone on to roles in industry and research labs.