Boosting Graph Robustness Against Backdoor Attacks: An Over-Similarity Perspective

Documenti analoghi

• Query-Based and Unnoticeable Graph Injection Attack from Neighborhood Perspective
  di: Liu, Chang, et al.
  Pubblicazione: (2025)
• ADBA:Approximation Decision Boundary Approach for Black-Box Adversarial Attacks
  di: Wang, Feiyang, et al.
  Pubblicazione: (2024)
• Composite Backdoor Attacks Against Large Language Models
  di: Huang, Hai, et al.
  Pubblicazione: (2023)
• Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
  di: Gosch, Lukas, et al.
  Pubblicazione: (2024)
• Less is More: on the Over-Globalizing Problem in Graph Transformers
  di: Xing, Yujie, et al.
  Pubblicazione: (2024)