Reinforcement learning-based secure training for adversarial defense in graph neural networks
Authors:
- Dongdong AnDADongdong An
- Xin GaoXGXin Gao
- Hongda QiHQHongda Qi
- Yang YangYYYang Yang
- Xin YeXYXin Ye
- Maozhen LiMLMaozhen Li
- Qin ZhaoQin Zhao
- 20 February 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 630
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62302308)
- East China Normal University
- National Key Research and Development Program of China (2022YFB4501704)
This publication has 12 references indexed in Scilit:
- Multiview-Ensemble-Learning-Based Robust Graph Convolutional Networks Against Adversarial AttacksIEEE Internet of Things Journal, 2024
- A graph-based interpretability method for deep neural networksNeurocomputing, 2023
- A Multiinterest and Social Interest-Field Framework for Financial SecurityIEEE Transactions on Computational Social Systems, 2023
- ERGCN: Data enhancement-based robust graph convolutional network against adversarial attacksInformation Sciences, 2022
- Learning safe neural network controllers with barrier certificatesFormal Aspects of Computing, 2021
- DeepEC: Adversarial attacks against graph structure prediction modelsNeurocomputing, 2021
- MGRL: Graph neural network based inference in a Markov network with reinforcement learning for visual navigationNeurocomputing, 2021
- Efficient and Stable Graph Scattering Transforms via PruningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretabilityComputer Science Review, 2020
- Statistical model checking for unbounded until formulasInternational Journal on Software Tools for Technology Transfer, 2015