Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations

Documenti analoghi

• AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
  di: Li, Jiate, et al.
  Pubblicazione: (2025)
• Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
  di: Li, Jiate, et al.
  Pubblicazione: (2025)
• Graph Neural Network Explanations are Fragile
  di: Li, Jiate, et al.
  Pubblicazione: (2024)
• Practicable Black-box Evasion Attacks on Link Prediction in Dynamic Graphs -- A Graph Sequential Embedding Method
  di: Li, Jiate, et al.
  Pubblicazione: (2024)
• Exact Certification of (Graph) Neural Networks Against Label Poisoning
  di: Sabanayagam, Mahalakshmi, et al.
  Pubblicazione: (2024)