Qusai Khaled

Qusai Khaled

PhD Candidate

• Research profile: AI Testing
• Research expertise: Testing AI systems, LLM security, NLP testing, AI auditing, hallucination detection, privacy risks, data security, performance evaluation, trust in LLMs, adversarial attacks, prompt injection, backdoor vulnerabilities, privacy protection, differential privacy, secure AI deployment, LLM-based agents, model robustness

Biography

Hasan Kaplan is a PhD candidate in the Data Governance group. He completed his undergraduate degree in computer engineering at Yaşar University in Turkey, followed by a master’s in electrical engineering at TU/e. He then pursued an engineering doctorate in software technology at TU/e, with a specialization in data engineering. His research focuses on testing large language models (LLMs) to identify security issues, such as hallucinations, privacy risks, adversarial attacks, and data security vulnerabilities, aiming to develop best practices for secure LLM deployment and improve their robustness and reliability.

Relevant academic links