Research & Projects
Research, course projects, industry experience, and personal experiments
Publications
DCInject: Persistent Backdoor Attacks via Frequency Manipulation in Personalized Federated Learning
Adaptive frequency-domain backdoor attack for Personalized Federated Learning (PFL) that achieves superior attack success rates while maintaining clean accuracy. Evaluated under parameter decoupling-based personalization.
Block Diagram
Attack Results
Defense ResultsOngoing Research
Agentic AI Vulnerabilities
Team research exploring vulnerabilities in agentic AI systems and autonomous agents.
Masters Research Project
EdgeML and Cybersecurity: Using Machine Learning Algorithms to detect impostor edge devices
This research focuses on security, specifically impersonation in a sensor network. This research is to build a light impostor detector ML model for edge devices. The model is also expected to detect sequence transitions if the impostor starts transmitting after its data is transmitted.
Course Projects
Blockchain-Based Healthcare Data Security
Proposed system integrating blockchain and IPFS for secure medical records management.
Malware Detection
Machine learning-based malware detection system with comprehensive analysis tools.
Industry Projects
CS Investigations Camera Solutions Platform
Developed comprehensive camera solutions platform for investigative purposes.
Dumpster Fullness Detection
Computer vision system for monitoring dumpster capacity and optimizing waste collection.
TinyML Tool Assessment and Prototyping
Evaluated and prototyped TinyML tools for edge device machine learning applications.
Fun Projects
Prime and Composite Classification
Created dataset of 2 million samples 1 million sample for each class, developed models using sequence models and 1D-CNN.