I’m currently a Staff Data Scientist at Obsidian Security, USA, where I apply data science and machine learning techniques to help secure SaaS applications against evolving cyber threats. My work spans across security-oriented generative AI applications, anomaly detection, time series analysis, and graph-based modeling. I also actively collaborate on applied AI research projects.
I hold a PhD in Computer Science from the State University of New York (SUNY) at Binghamton, USA, completed under the supervision of Professor Ping Yang and Professor Guanhua Yan, where my research was centered on the intersection of Machine Learning (ML) and Cybersecurity — with an emphasis on Explainable AI and Adversarial Machine Learning. My doctoral work included applications in malware classification and anomaly detection.
Prior to my PhD, I earned a Bachelor’s degree (Hons) in Computational Physics from the University of Colombo, Sri Lanka. Earlier in my career, I worked on a range of research projects in robotics, wireless communications, and blockchain-based secure distributed systems. These experiences helped me build foundations in Markovian modeling, deep learning, simulations, and scientific workflow management using blockchain technologies.
Research
Please refer to my Google Scholar profile for the most up-to-date list of publications.
- Virtual Machine Proactive Fault Tolerance using Log-based Anomaly Detection
IEEE Access, 2024
[code] - Exploring Machine Learning and Deep Learning Approaches for Multi-Step Forecasting in Municipal Solid Waste Generation
IEEE Access, 2022
[code]
*Authors contributed equally to the work - CFGExplainer: Explaining Graph Neural Network-Based Malware Classification from Control Flow Graphs
IEEE/IFIP DSN, 2022
[code] - Real-Time Evasion Attacks Against DL-Based Anomaly Detection from Distributed System Logs
ACM CODASPY, 2021
[presentation video] [code] - RAMP: Real-Time Anomaly Detection in Scientific Workflows
IEEE Big Data, 2019
[extended] [code] [slides] - SciBlock: A Blockchain-Based Tamper-Proof Non-Repudiable Storage for Scientific Workflow Provenance
IEEE CIC, 2019
[slides] - DeepChannel: Wireless Channel Quality Prediction using Deep Learning
IEEE TVT, 2019
[code] - A Deep Learning Model for Wireless Channel Quality Prediction
IEEE ICC, 2019
[code] - A Markovian Model for Analyzing Opportunistic Request Routing in Wireless Cache Networks
IEEE TVT, 2018
[code] [slides] - Analyzing Opportunistic Request Routing in Wireless Cache Networks
IEEE ICC, 2018
[code] - Simulation of Symmetric and Asymmetric Movement Gaits for Lateral Undulation in Serial Snake Robots
ICCMS, 2017
- Comparison of Serial and Parallel Snake Robots for Lateral Undulation Motion Using Gazebo
IEEE ICIAfS, 2016
[code]
Dissertations
- Empowering Artificial Intelligence for Cybersecurity Applications
(2022).
PhD Dissertation, State University of New York (SUNY) at Binghamton, USA - Simulation of a Snake Robot
(2016).
Undergraduate Dissertation, University of Colombo, Sri Lanka
Mentoring
- Dinushan Vimukthi – University of Colombo (2024–present)
- Nadeesha Epa – University of Colombo (2024–present)
- Pratheek Senevirathne – University of Colombo (2023–2024)
- Maheeka Solangaarachchige – University of Colombo (2023)
- Achini Wijayathunge – University of Colombo (2023)
- Oshan Ivantha – University of Colombo (2021–2023)
- Disni Rathnayake – University of Colombo (2021–2023)
- Austin Barr – SUNY Brockport (2022–2023)