PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization

Documenti analoghi

• Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory
  di: Mohammady, Meisam, et al.
  Pubblicazione: (2026)
• Universally Harmonizing Differential Privacy Mechanisms for Federated Learning: Boosting Accuracy and Convergence
  di: Feng, Shuya, et al.
  Pubblicazione: (2024)
• LMO-DP: Optimizing the Randomization Mechanism for Differentially Private Fine-Tuning (Large) Language Models
  di: Yang, Qin, et al.
  Pubblicazione: (2024)
• DPI: Ensuring Strict Differential Privacy for Infinite Data Streaming
  di: Feng, Shuya, et al.
  Pubblicazione: (2023)
• DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
  di: Zhang, Xinwei, et al.
  Pubblicazione: (2024)