Shahaf Bassan

Hey world! 👋 I’m Shahaf, a PhD student at the Hebrew University of Jerusalem, working under the supervision of Prof. Guy Katz.

My research lies in the area of explainability and interpretability, which aims to help humans better understand how machine learning models make decisions. While many interpretability methods exist, some of the strongest approaches today still rely on “hand-waving” arguments rather than formal, provable guarantees, which makes it difficult to fully trust them.

🎓 In my PhD research, I work on bringing mathematical rigor to interpretability, studying explanation methods through the lenses of verification, computational complexity, and machine learning theory. My research covers both the theoretical and the practical sides of this topic.

I have previously interned at IBM Research, and am one of the organizers of the Theory of Interpretable AI online seminar.

Feel free to reach me via email or connect through my social profiles 🙂:

shahaf.bassan@gmail.com