I’m using advanced natural language processing (NLP) to improve software security by identifying vulnerabilities, detecting malicious patterns, inferring authorship, or adding context-aware components to traditional analysis. To this end, I’m exploring optimized code representations to improve the performance of these models. By integrating machine learning and large language models (LLMs) into software engineering, I aim to create more efficient security tools. Currently, I’m developing a multi-agent framework for automated program repair and investigating adversarial attacks on AI systems, such as prompt stealing in generative models like stable diffusion.

Please reach out to collaborate 😃