Documenti analoghi

• Injecting Bias into Text Classification Models using Backdoor Attacks
  di: Yavuz, A. Dilara, et al.
  Pubblicazione: (2024)
• Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
  di: Zhu, Mingyan, et al.
  Pubblicazione: (2023)
• Hide in Plain Sight: Clean-Label Backdoor for Auditing Membership Inference
  di: Chen, Depeng, et al.
  Pubblicazione: (2024)
• A Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
  di: Dai, Jiazhu, et al.
  Pubblicazione: (2025)
• Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
  di: Zhi, Yuhan, et al.
  Pubblicazione: (2025)