arXiv Artificial Intelligence

Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks

1 hour ago 30.09.2026 07:00 👁 1 views
Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks

Quick summary

arXiv:2609.37972v1 Announce Type: cross Abstract: As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat. By querying a victim model's black-box API, an adversary can construct a functionally equivalent surrogate model, compromising proprietary intellectual property and downstream security. Existing GNN stealing attacks, however, rely on overly permissive assumptions, such as soft-label outputs, large query budgets, full-graph query access, and prior knowledge of victim backbones that

Key takeaways

  • arXiv:2609.37972v1 Announce Type: cross Abstract: As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat.
  • By querying a victim model's black-box API, an adversary can construct a functionally equivalent surrogate model, compromising proprietary intellectual property and downstream security.
  • Existing GNN stealing attacks, however, rely on overly permissive assumptions, such as soft-label outputs, large query budgets, full-graph query access, and prior knowledge of victim backbones that

Why it matters

“Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks” should be evaluated beyond branding and benchmark scores. Its practical importance will emerge in task accuracy, latency, unit cost, safety and integration with real workflows.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗