DEV SARAWAT

Positive and analytical, with strong foundation in machine learning principles and techniques. Possesses essential knowledge in data preprocessing and model development, with proficiency in Python and TensorFlow. Capable of leveraging technical skills to drive impactful machine learning solutions.

Explainable Machine Learning for Cyberattack Identification from Traffic Flows, IEEE

• Designed a deep learning anomaly detection system using only traffic flow data to identify cyberattacks in urban traffic networks.
• Implemented explainable AI techniques (LIME, occlusion sensitivity) to improve model transparency and trust.
• Created a virtual city network simulation to analyze real-world attack scenarios and traffic responses.
• Identified critical features and addressed unique challenges in cyberattack detection, guiding future model development.

Machine Learning for Cyber-Attack Identification from Traffic Flows, IEEE

• Built a simulation and ML framework combining cyber-attack and traffic flow analysis for smart city systems.
• Evaluated and benchmarked Random Forest, SVM, and CNN models, achieving up to 85% accuracy with traffic data alone.
• Established “Max Halting Duration” and “Jam Length” as robust attack indicators for automated detection.
• Released open-source tools and insights to advance real-world transportation cybersecurity research.