Explore the vulnerabilities of inductive graph neural networks in this 18-minute IEEE conference talk, delving into model stealing attacks. Learn from experts Yun Shen, Xinlei He, Yufei Han, and Yang Zhang as they discuss potential security risks and implications for graph-based machine learning models.
Model Stealing Attacks Against Inductive Graph Neural Networks
Overview
Syllabus
Model Stealing Attacks Against Inductive Graph Neural Networks
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Model Orthogonalization - Class Distance Hardening in Neural Networks for Better Security
-
WtaGraph - Web Tracking and Advertising Detection using Graph Neural Networks
-
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
-
OblivGNN: Oblivious Inference on Transductive and Inductive Graph Neural Networks
-
D-DAE - Defense-Penetrating Model Extraction Attacks
-
SoK - Certified Robustness for Deep Neural Networks
