Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks

Ähnliche Einträge

• SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
  von: Zhang, Yuxiang, et al.
  Veröffentlicht: (2026)
• How Explanations Leak the Decision Logic: Stealing Graph Neural Networks via Explanation Alignment
  von: Ma, Bin, et al.
  Veröffentlicht: (2025)
• LiSA: Leveraging Link Recommender to Attack Graph Neural Networks via Subgraph Injection
  von: Zhang, Wenlun, et al.
  Veröffentlicht: (2025)
• A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
  von: Dai, Jiazhu, et al.
  Veröffentlicht: (2025)
• A Clean-graph Backdoor Attack against Graph Convolutional Networks with Poisoned Label Only
  von: Dai, Jiazhu, et al.
  Veröffentlicht: (2024)