Salijona Dyrmishi

Hi! I’m a researcher at the SnT research center (University of Luxembourg), working at the intersection of AI/ML and Cybersecurity.

My research focuses on making AI/ML systems more secure and trustworthy, especially against adversarial attacks. I’m particularly interested in high-stakes domains like malware detection or fraud prevention, where small vulnerabilities can have serious consequences. Recently, I’ve also been exploring synthetic data for tabular datasets.

If you’d like a quick overview, here’s a 5-minute pitch video with the motivation, the challenges, and what makes this research both exciting and necessary.

Before moving to Luxembourg for my PhD, I completed my Master’s at the University of Tartu in Estonia and my Bachelor’s at the University of Tirana in Albania, including a one-year exchange at NTNU in Norway.

Always happy to chat about adversarial threats and defenses in AI/ML, feel free to get in touch!