Graph Transformers are shown to be vulnerable to adaptive structure-perturbation attacks, which can also be used for effective adversarial training to improve robustness.
Adversarial training for graph neu- ral networks: Pitfalls, solutions, and new directions
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
-
Adversarial Robustness of Graph Transformers
Graph Transformers are shown to be vulnerable to adaptive structure-perturbation attacks, which can also be used for effective adversarial training to improve robustness.