My name is Sebastian and I'm a tenured track assistant professor at the Department of Computer Science at Aalto University. I lead Trustworthy & Adversarial Computing Lab (group GitHub). I work on trustworthy machine learning and adjacent topics.
You can get a better idea by looking at my publication list (Google Scholar) or blog posts.
Here you can find the forks of the official releases of my scientific work:
- LLMart a toolkit for generating adversarial prompts
- ML pipeline attestation with Atlas
- model watermarking with DAWN
- PRADA defence against model extraction
- conflicts in ML protection mechanisms
- clustering for fraud detection
as well as some tinkering projects:
(I use neovim, btw)