Biography
I am a PhD student in the Research Group Data Mining and Machine Learning at the University of Vienna, supervised by Prof. Claudia Plant. I am interested in understanding how neural networks organize information in their embedding space, and in developing principled methods to make learned representations more robust, fair, and trustworthy.
Broadly, my interests span representation learning, adversarial robustness, fairness in machine learning, and AI safety. I enjoy research that combines empirical work with theoretical analysis, and I am drawn to questions where careful reasoning about geometry and information can lead to simple, principled solutions.
Download my CV.
Interests
- Representation Learning
- Adversarial Robustness
- Fairness in ML
- Deep Clustering
- Reinforcement Learning
- AI Safety
Education
Research Areas
Representation Learning
Understanding how deep networks structure information in their embedding spaces, and learning representations that are useful for downstream tasks.
Fairness
Building models whose decisions do not rely on sensitive attributes, with formal notions of fairness backed by theoretical guarantees.
Adversarial Robustness
Studying how and why neural networks fail under small perturbations, and developing principled ways to make them more resilient.
AI Safety
Making powerful models reliable and aligned with human intent, with an interest in unlearning, deception detection, and interpretability.
Publications
* denotes equal contribution
News
Contact
I am always open to collaboration and happy to chat about research ideas. If you're working on something related or just want to connect, feel free to reach out!
- andrii.shkabrii@univie.ac.at
- Vienna, Austria