research
∙
02/06/2023
Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks
In tasks like node classification, image segmentation, and named-entity ...
share
research
∙
01/05/2023
Randomized Message-Interception Smoothing: Gray-box Certificates for Graph Neural Networks
Randomized smoothing is one of the most promising frameworks for certify...
research
∙
01/02/2023
Training Differentially Private Graph Neural Networks with Random Walk Sampling
Deep learning models are known to put the privacy of their training data...
research
∙
11/25/2022
Invariance-Aware Randomized Smoothing Certificates
Building models that comply with the invariances inherent to different d...
research
∙
10/28/2022
Localized Randomized Smoothing for Collective Robustness Certification
Models for image segmentation, node classification and many other tasks ...
research
∙
10/21/2021
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
End-to-end (geometric) deep learning has seen first successes in approxi...
research
∙
05/08/2019