1 code implementation • 27 Apr 2024 • Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström
In this work, we theoretically define the concept of expected robustness in the context of attributed graphs and relate it to the classical definition of adversarial robustness in the graph representation learning literature.
1 code implementation • 21 Feb 2024 • Sofiane Ennadir, Yassine Abbahaddou, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström
Successful combinations of our NoisyGNN approach with existing defense techniques demonstrate even further improved adversarial defense results.