AINeutralarXiv – CS AI · 7h ago6/10
🧠
GJDNet: Robust Graph Neural Networks via Joint Disentangled Learning Against Adversarial Attacks
Researchers propose GJDNet, a robust Graph Neural Network defense framework that protects against adversarial attacks by jointly disentangling node representations and decision spaces. The approach addresses vulnerabilities in GNNs caused by adversarial perturbations that invert graph connectivity patterns, achieving improved robustness across different graph types.