Lukas Gosch

A beautiful, simple, clean, and responsive Jekyll theme for academics

Codebase for papers "Exact Certification of (Graph) Neural Networks against Label Poisoning" and "Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks"

The codebase used to generate the reults in the ICLR 2023 paper "Revisiting Robustness in Graph Machine Learning".

Codebase used to generate the results for NeurIPS23 "Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions" paper.