I am a PhD fellow at the Machine Learning Section of the University of Copenhagen
with a focus on Unlearning, Robustness and Privacy.
I am supervised by Prof. Amartya Sanyal
and Prof. Amir Yehudayoff.
| Master's thesis |
Adversarial Resilience against Clean-Label Attacks in Realizable and Noisy Settings Carolin Heinzler | arXiv, 2024 We investigate the challenge of establishing stochastic-like guarantees when learning from a stream of i.i.d. data with clean-label adversarial samples. Introducing the notion of a clean-label adversary in the agnostic context, we are the first to give a theoretical analysis of a disagreement-based learner for thresholds. |