Revisiting Training-Inference Trigger Intensity in Backdoor Attacks

Documenti analoghi

• Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
  di: Zhi, Yuhan, et al.
  Pubblicazione: (2025)
• Impart: An Imperceptible and Effective Label-Specific Backdoor Attack
  di: Zhao, Jingke, et al.
  Pubblicazione: (2024)
• CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
  di: Zheng, Jingyi, et al.
  Pubblicazione: (2024)
• Invisible Textual Backdoor Attacks based on Dual-Trigger
  di: Hou, Yang, et al.
  Pubblicazione: (2024)
• ME: Trigger Element Combination Backdoor Attack on Copyright Infringement
  di: Yang, Feiyu, et al.
  Pubblicazione: (2025)