Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models

Documenti analoghi

• Invisible Backdoor Attacks on Diffusion Models
  di: Li, Sen, et al.
  Pubblicazione: (2024)
• HaloProbe: Bayesian Detection and Mitigation of Object Hallucinations in Vision-Language Models
  di: Zohrabi, Reihaneh, et al.
  Pubblicazione: (2026)
• Diffusion Classifiers Understand Compositionality, but Conditions Apply
  di: Jeong, Yujin, et al.
  Pubblicazione: (2025)
• VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
  di: Chou, Sheng-Yen, et al.
  Pubblicazione: (2023)
• CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
  di: Zhang, Jinghuai, et al.
  Pubblicazione: (2022)