Graph Convolutional Network Robustness Verification Algorithm Based on Dual Approximation
- 29 November 2024
- book chapter
- Published by Springer Nature
- p. 146-161
Abstract
No abstract availableKeywords
This publication has 17 references indexed in Scilit:
- Heterogeneous Manycore Architectures Enabled by Processing-in-Memory for Deep Learning: From CNNs to GNNs: (ICCAD Special Session Paper)2021
- Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation2021
- Spatial-temporal graph neural network for traffic forecasting: An overview and open research issuesApplied Intelligence, 2021
- Adversarial Immunization for Certifiable Robustness on Graphs2021
- A Dual Heterogeneous Graph Attention Network to Improve Long-Tail Performance for Shop Search in E-Commerce2020
- Certifiable Robustness of Graph Convolutional Networks under Structure Perturbations2020
- Certified Robustness of Community Detection against Adversarial Structural Perturbation via Randomized Smoothing2020
- Certifiable Robustness and Robust Training for Graph Convolutional Networks2019
- Adversarial Attacks on Neural Networks for Graph Data2018
- Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks2017