The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes

Documenti analoghi

• Graph-Aware Stealthy Poison-Text Backdoors for Text-Attributed Graphs
  di: Luo, Qi, et al.
  Pubblicazione: (2026)
• Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
  di: Nguyen, Quang H., et al.
  Pubblicazione: (2024)
• Poisoning the Inner Prediction Logic of Graph Neural Networks for Clean-Label Backdoor Attacks
  di: Zhang, Yuxiang, et al.
  Pubblicazione: (2026)
• Provable Robustness Against a Union of $\ell_0$ Adversarial Attacks
  di: Hammoudeh, Zayd, et al.
  Pubblicazione: (2023)
• Training Data Influence Analysis and Estimation: A Survey
  di: Hammoudeh, Zayd, et al.
  Pubblicazione: (2022)