Presents the first certification technique for (non-)robustness of GCNs to L0-bounded perturbations on binary node attributes, together with a joint robust semi-supervised training procedure.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A taxonomy and re-implementation study of 12 ML Android malware detectors finds persistent vulnerabilities to malware evolution and adversarial attacks due to insufficient capture of malware semantics.
citing papers explorer
-
Certifiable Robustness and Robust Training for Graph Convolutional Networks
Presents the first certification technique for (non-)robustness of GCNs to L0-bounded perturbations on binary node attributes, together with a joint robust semi-supervised training procedure.
-
Unraveling the Key of Machine Learning-based Android Malware Detection
A taxonomy and re-implementation study of 12 ML Android malware detectors finds persistent vulnerabilities to malware evolution and adversarial attacks due to insufficient capture of malware semantics.