An explanation-based detector using seven novel metrics derived from GNN explanations identifies backdoored graphs with high performance on benchmark datasets against multiple attack models.
Advances in neural information processing systems 33, 19620–19631 (2020) 5, 1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Identifying Backdoored Graphs in Graph Neural Network Training: An Explanation-Based Approach with Novel Metrics
An explanation-based detector using seven novel metrics derived from GNN explanations identifies backdoored graphs with high performance on benchmark datasets against multiple attack models.