I am Maciej Chrabaszcz, a PhD student at Warsaw University of Technology (WUT). My research area lies in the field of exploratory model analysis, where I use adversarial and Explainable AI (XAI) methods to uncover insights about models.
My doctoral research is centered on the strategic evaluation of AI Foundation Models through red teaming approaches, aiming to enhance their robustness and reliability.
Should you wish to discuss my research or have any inquiries, feel free to contact me at: [email protected]