Adversarial Robustness of Graph Neural Networks

MCML Authors

Daniel Zügner

Dr.

* Former Member

→ Group Stephan Günnemann
 Data Analytics & Machine Learning

Abstract

In this thesis we look at graph neural networks (GNNs) from a perspective of adversarial robustness. We generalize the notion of adversarial attacks -- small perturbations to the input data deliberately crafted to mislead a machine learning model -- from traditional vector data such as images to graphs. We further propose robustness certification procedures for perturbations of the node attributes as well as the graph structure.

phdthesis

---

Dissertation

TU München. May. 2022

---

Authors

D. Zügner

---

Links

URL

---

Research Area

 A3 | Computational Models