M. Bilgehan Ertan
PhD Student in AI Safety & Privacy, CWI Amsterdam
Amsterdam, Netherlands
I am Bilgehan, a researcher at the intersection of AI safety, privacy, and machine learning, currently pursuing my PhD at CWI (Centrum Wiskunde & Informatica) in Amsterdam under the supervision of Prof. Marten van Dijk.
I hold a BSc in Computer Science and Engineering from Sabancı University, Türkiye, and an MSc in Computer Security (cum laude) from Vrije Universiteit Amsterdam. Beyond my academic research, I have professional experience as a Security Researcher and Developer at PRODAFT.
My research focuses on building safe, secure, and privacy-preserving AI systems, combining theoretical analysis with practical engineering. I study how information leaks and adversarial behavior arise in modern AI, developing formal frameworks based on Differential Privacy, f-DP, and PAC privacy to understand and bound these effects. I also work on adversarial and membership inference attacks on large language models to evaluate and strengthen their real-world resilience. More recently, my work has expanded from privacy toward the broader question of AI safety. Together with Prof. Srini Devadas at MIT, I study certified defenses against data poisoning in LLM post-training, as well as the safety of agentic systems.
I’m broadly interested in how we can make AI systems safe, secure, and private while remaining practically useful.