DP-SGD (Differential Privacy SGD) + Federated FT: Opacus + Flower
Privacy guarantees for FT with sensitive data: DP-SGD (Opacus library) — add controlled noise to gradients, (ε, δ)-differential privacy guarantee. Federated FT (Flower) — data never reaches server, only gradients. Ideal for KVKK + health + finance. Privacy budget vs accuracy trade-off.
Şükrü Yusuf KAYA
26 min read
Advanced
✅ Teslim
- Opacus install + mini DP-SGD pilot. 2) Privacy budget ε=8 ile accuracy delta ölç. 3) Sonraki ders: 18.10 — ROOTS Data Transparency.
Yorumlar & Soru-Cevap
(0)Yorum yazmak için giriş yap.
Yorumlar yükleniyor...
Related Content
Part 0 — Engineering Foundations
Welcome to the Fine-Tuning Cookbook: System, Stage Taxonomy, and the Reproducibility Contract
Start LearningPart 0 — Engineering Foundations
Reproducibility Stack: Seeds, cuDNN Flags, and Deterministic CUDA — End the 'Works on My Machine' Problem
Start LearningPart 0 — Engineering Foundations