Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Documenti analoghi

• DeDe: Detecting Backdoor Samples for SSL Encoders via Decoders
  di: Hou, Sizai, et al.
  Pubblicazione: (2024)
• Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
  di: Yao, Duanyi, et al.
  Pubblicazione: (2024)
• URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
  di: Yao, Duanyi, et al.
  Pubblicazione: (2024)
• Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models
  di: Wang, Kai, et al.
  Pubblicazione: (2026)
• Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
  di: Yan, Jun, et al.
  Pubblicazione: (2023)