What I do

I want to make research on reliable AI accessible. I am doing a PhD on this, so you don't have to. I am very happy to give talks that bring technical insights straight to you.

Publications Contact me

Santa Claus in an arm wrestling match against batman; cyberpunk

Talks

You got questions? I got answers!

I have given several talks and am happy to give more, especially on:

AI Security
AI Legislation
Adversarial Robustness

Invite me

Blog posts

Pitfalls of Interpretability

3 times when interpretability wasn't interpretable.

March 24, 2023

17 mins read

# Deep Learning | Interpretability

Catastrophically Confident Classifiers

Does your AI know when it doesn't know?

November 03, 2022

13 mins read

# Deep Learning | Out-of-Distribution Detection | Adversarial Robustness

Attacking AI for Fun and Profit

How I won an ML Security Evasion Competition.

October 09, 2022

14 mins read

# Deep Learning | Testing ML | Adversarial Robustness

View All Posts →