JiangChSo/PFLM

Kegunaan

JiangChSo/PFLM adalah repositori GitHub publik, terutama memakai Jupyter Notebook. Snapshot terakhir yang disimpan mencatat 31 bintang dan 6 fork. Topik: blockchain, federated learning, membership, privacy preserving, privacy preserving machine learning. Baca dokumentasi, lisensi, dan issue terkini sebelum memakai perangkat lunaknya.

Privacy-preserving federated learning is distributed machine learning where multiple collaborators train a model through protected gradients. To achieve robustness to users dropping out, existing practical privacy-preserving federated learning schemes are based on (t, N)-threshold secret sharing. Such schemes rely on a strong assumption to guarantee security: the threshold t must be greater than half of the number of users. The assumption is so rigorous that in some scenarios the schemes may not be appropriate. Motivated by the issue, we first introduce membership proof for federated learning, which leverages cryptographic accumulators to gen

Repositori GitHub

Bintang

31

Bintang bertambah · 7 hari

—

Fork

6

Bahasa utama

Jupyter Notebook

Lisensi repositori

Belum diperiksa

Push kode terakhir

9 Jun 2021

Popularitas dari bintang GitHub. Pertumbuhan 7 hari perlu sepekan cuplikan lokal. Ini koleksi kami, bukan tren resmi GitHub.

Sumber & kebaruan data

Entri impor menautkan sumber. Entri membantu penemuan, bukan dukungan.