Current Research Projects

Configuration hardening in software systems is a complex challenge in IT due to the vast number of configuration parameters. Our goal is to develop an AI-powered automated configuration management system that combines efficient configuration hardening with proactive defense strategies against attacks on misconfigures applications.

​LLMs have transformed how we interact with the internet, impacting various sectors through widespread adoption. They simplify customer experiences and automate tasks such as content generation, summarization, and Q&A. However, their adoption brings significant security and privacy challenges. Our work focuses on examining these implications within the financial sector, exploring how LLMs can be used securely and ethically in banking to enhance trust and resilience.

​

AI has revolutionized the use of Electronic Health Records (EHR) in the medical field by enhancing efficiency, accuracy, and patient care. Now LLMs are transforming the role of EHR by enabling more intuitive and intelligent interactions with medical data. By integrating LLMs into EHRs, healthcare providers can streamline workflows, reduce documentation burden, and improve decision-making for better patient outcomes. We explore the impact of privacy and security attacks on sensitive EHR data that uses LLMs.

Traditionalpassword-based authentication methods are inefficient and prone to attacks. Real-time facial recognition offers a secure alternative by ensuring only authorized users perform sensitive transactions. This project focuses on developing robust, accurate, and user-friendly biometric verification methods while addressing the critical threat of adversarial machine learning (AML) attacks. AML attacks exploit vulnerabilities in biometric systems, reverse-engineering raw biometric data to mimic recognition models and enable unauthorized access. We first aim to explore and analyze face recognition and verification methods in online banking and study adversarial attack techniques and defense strategies to enhance biometric security.