Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models

Documenti analoghi

• CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
  di: Lai, Songning, et al.
  Pubblicazione: (2024)
• Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Models
  di: Lai, Songning, et al.
  Pubblicazione: (2024)
• Mitigating Spurious Background Bias in Multimedia Recognition with Disentangled Concept Bottlenecks
  di: Huang, Gaoxiang, et al.
  Pubblicazione: (2025)
• Backdooring CLIP through Concept Confusion
  di: Hu, Lijie, et al.
  Pubblicazione: (2025)
• Rethinking Robust Adversarial Concept Erasure in Diffusion Models
  di: Yin, Qinghong, et al.
  Pubblicazione: (2025)