Research

Exploring the frontiers of AI for Software Engineering and Software Engineering for AI through innovative research methodologies

AI4SE

Applying machine learning techniques to enhance software engineering practices, including automated testing, vulnerability detection, and code analysis.

ML-guided TestingVulnerability Detection

SE4AI

Bringing software engineering rigor to AI systems through systematic testing, explanation techniques, and robust development methodologies.

Model TestingExplainable AI
Research

ML-Guided Vulnerability Detection in Smart Contracts

A novel approach combining machine learning with symbolic execution to automatically detect and classify security vulnerabilities in smart contract code.

December 15, 2024
Research Project
Machine LearningSecuritySmart ContractsVulnerability Detection
Active Research
View Details
Research

Explanation-Guided Symbolic Execution for Software Testing

Integrating explainable AI techniques with symbolic execution to generate human-interpretable test cases and improve debugging efficiency in complex software systems.

November 20, 2024
Research Project
Symbolic ExecutionExplainable AISoftware TestingDebugging
Active Research
View Details

Current Research Focus

My research spans two interconnected domains: applying AI to improve software engineering practices and bringing software engineering principles to AI development. This bidirectional approach creates synergies that advance both fields while addressing real-world challenges in software security, testing, and AI system reliability.

Actively pursuing PhD research at University of Texas, Arlington