Experience

Cybersecurity Lab (UArk Affiliated)

• Reinforcement Learning for Fuzzing: Developed RL-based models to generate test cases, significantly improving vulnerability detection and code coverage over traditional fuzzing techniques.
• Master’s Thesis – AI-Based Anomaly Detection: Working on machine learning models for real-time anomaly detection in water systems, enhancing security and resilience of cyber-physical infrastructure.

UArk Affiliated

• Image Synthesis and Reconstruction: Used Denoising Diffusion Probabilistic Model on ALOT dataset to generate diverse, high-fidelity artificial textures.
• Deep Learning-based Steganography: Implemented a framework to securely embed one image within another, ensuring high imperceptibility and robust recoverability.
• Latent Diffusion Models: Implemented LDMs for efficient text-to-image generation by applying diffusion in latent space using pretrained autoencoders.

Reinforcement Learning for Traffic Optimization (IIIT-H Affiliated)

• Optimized lane-level dynamics and vehicle-to-vehicle communication by simulating multi-modal traffic environments using SUMO.
• Enhanced lane selection and emergency vehicle dynamics by developing SB3-based reinforcement learning models.
• Reduced traversal times significantly by evaluating RL strategies on grid-world and real-world-inspired road networks.

CODEVENTURE TECH LLP

• Streamlined operations by optimizing workflows and improving team communication, boosting overall efficiency.
• Designed and developed a city complaint management system using PHP, WordPress, HTML, CSS, and JavaScript, enhancing civic issue reporting and response times.