Lists (10)
Stars
SPU (Secure Processing Unit) aims to be a provable, measurable secure computation device, which provides computation ability while keeping your private data protected.
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Official implementation for AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE. The paper is presented at the 33rd USENIX Security Symposium, 2024.
PyTorch Implementation of the Maximum a Posteriori Policy Optimisation
Supplementary code for the paper "UnSplit: Data-Oblivious Model Inversion, Model Stealing, and Label Inference Attacks Against Split Learning".
[ICML 2022 / ICLR 2024] Source code for our papers "Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks" and "Be Careful What You Smooth For".
[KDD 2022] "Bilateral Dependency Optimization: Defending Against Model-inversion Attacks"
GPU/CUDA implementation of Leveled BFV/CKKS/BGV scheme.
nGraph-HE: Deep learning with Homomorphic Encryption (HE) through Intel nGraph
This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.
This repository contains the evaluation code for the NDSS 2024 paper: MPCDIFF: Testing and Repairing MPC-Hardened Deep Learning Models.
Characterizing and Optimizing End-to-End Systems for Private Inference
Papers and resources related to the security and privacy of LLMs 🤖
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Privacy-Preserving Convolutional Neural Networks using Homomorphic Encryption
Privacy-Preserving Computing Platform 由密码学专家团队打造的开源隐私计算平台，支持多方安全计算、联邦学习、隐私求交、匿踪查询等。
A framework for Privacy Preserving Machine Learning
Pytorch implementation of our paper accepted by IEEE TNNLS, 2022 — Carrying out CNN Channel Pruning in a White Box
FudanMPL 2.0, a series of multi-party learning frameworks, with rich features, including secure and fast XGBoost, secure Fine-tuning for pre-trained models, and open source SecureML.
SecMML (Queqiao): Secure MPC (multi-party computation) Machine Learning Framework.