MAGIA: Sensing Per-Image Signals from Single-Round Averaged Gradients for Label-Inference-Free Gradient Inversion

Documenti analoghi

• Adaptive Gradient Calibration for Single-Positive Multi-Label Learning in Remote Sensing Image Scene Classification
  di: Liu, Chenying, et al.
  Pubblicazione: (2025)
• MGIC: A Multi-Label Gradient Inversion Attack based on Canny Edge Detection on Federated Learning
  di: Liu, Can, et al.
  Pubblicazione: (2024)
• Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
  di: Wang, Yanbo, et al.
  Pubblicazione: (2024)
• PerSense: Training-Free Personalized Instance Segmentation in Dense Images
  di: Siddiqui, Muhammad Ibraheem, et al.
  Pubblicazione: (2024)
• AFGI: Towards Accurate and Fast-convergent Gradient Inversion Attack in Federated Learning
  di: Liu, Can, et al.
  Pubblicazione: (2024)