Title |
|---|
 Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary PerturbationsComputer Vision and Pattern Recognition (CVPR), 2025 |
 Certifiable Black-Box Attacks with Randomized Adversarial Examples:
Breaking Defenses with Provable ConfidenceConference on Computer and Communications Security (CCS), 2023 |
 A Certified Radius-Guided Attack Framework to Image Segmentation ModelsEuropean Symposium on Security and Privacy (Euro S&P), 2023 |
 Efficient, Direct, and Restricted Black-Box Graph Evasion Attacks to
Any-Layer Graph Neural Networks via Influence FunctionWeb Search and Data Mining (WSDM), 2020 |
 Benchmarking Graph Neural NetworksJournal of machine learning research (JMLR), 2023 |
