Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
Dagger, a novel two-phase decoupling-based attack framework that consistently outperforms state-of-the-art GNN stealing attacks, achieving up to 18.16\% higher fidelity while only utilizing 12.23$\times$ fewer queries than the strongest baseline.
Ying Song, Xiao-Wei Jia, Balaji Palanisamy
· 0 citations