Erasing Self-Supervised Learning Backdoor by Cluster Activation Masking

Documenti analoghi

• BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
  di: Wang, Yifei, et al.
  Pubblicazione: (2024)
• BlindU: Blind Machine Unlearning without Revealing Erasing Data
  di: Wang, Weiqi, et al.
  Pubblicazione: (2026)
• Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
  di: Tian, Zhihua, et al.
  Pubblicazione: (2025)
• Backdoor Attacks against Image-to-Image Networks
  di: Jiang, Wenbo, et al.
  Pubblicazione: (2024)
• CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
  di: Jin, Haibo, et al.
  Pubblicazione: (2021)