Graduate researcher building active defense systems for critical infrastructure. From bare-metal servers to adaptive honeytokens — I secure the things that power our world.
I'm a cybersecurity graduate student at Northeastern University's Khoury College with a background in computer science from BITS Pilani, Dubai.
My work sits at the intersection of security engineering, cloud infrastructure, and active defense. I build systems that don't just detect threats — they engage, deceive, and contain them. My current research focuses on honeytoken-based deception frameworks for EV charging infrastructure.
Before the formal education, I cut my teeth on real infrastructure — provisioning bare-metal servers, configuring firewalls, mitigating DDoS attacks, and running high-traffic game server networks. That hands-on foundation drives everything I do today.
Designed a three-stage active defense pipeline — risk scoring, adaptive response, and deception & containment — for EV charging stations. The framework targets reconnaissance, MITM, and coordinated grid attack scenarios on ISO 15118/OCPP flows.
Developed a weighted risk-scoring algorithm and adaptive honeytoken system that routed high-risk sessions into an isolated sandbox, achieving zero false-positive sandboxing of legitimate users across 50,000 simulated sessions. Engineered as a lightweight software agent (<5% CPU overhead) deployable via firmware updates on existing EVSE controllers.
Engineered a 3-factor authentication system combining HoneyTokens, Canvas Fingerprinting, and Graphical Passwords using Node.js and Express.js. Achieved 100% detection of unauthorized credential use and 99.1% browser identification accuracy via fingerprintJS.
Secured against shoulder-surfing with a recognition-based 4×4 randomized image grid (43,680 combinations) and automated email OTP verification for all unrecognized device logins.
Developed a modified W-Net deep learning architecture, training on the BraTS dataset (369 multi-modal MRI scans). Achieved 98.54% accuracy and a Dice score of 0.9857 in classifying tumor regions (Enhancing Tumor, Tumor Core, Whole Tumor).
Engineered a sensor fusion system for a TurtleBot, integrating intent-aware SLAM and monocular camera data to improve pathfinding accuracy by 30%. Implemented a Gumbel Social Transformer model for pedestrian trajectory prediction and optimized it to reduce computational latency by 40%.