Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

Documenti analoghi

• Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
  di: Wang, Yanbo, et al.
  Pubblicazione: (2025)
• R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
  di: Sheng, Lijun, et al.
  Pubblicazione: (2025)
• Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
  di: Struppek, Lukas, et al.
  Pubblicazione: (2023)
• Approximating Optimal Morphing Attacks using Template Inversion
  di: Colbois, Laurent, et al.
  Pubblicazione: (2024)
• Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
  di: Sami, Hasin Us, et al.
  Pubblicazione: (2025)