ZeroGAR: Benchmarking the Adversarial Robustness of Zero-Shot Graph Models
The proposed ZeroGAR is the first systematic benchmark for evaluating the adversarial robustness of ZGMs and reveals that strong clean zero-shot performance does not guarantee adversarial robustness, with three key findings.
Zhong-Jian Zhang, Xiao Wang, Bu-Sheng Zhang et al.
· 0 citations