Stars
A framework for secure, handy, accurate, and fast transformer inference
PYthon For Homomorphic Encryption Libraries, perform encrypted computations such as sum, mult, scalar product or matrix multiplication in Python, with NumPy compatibility. Uses SEAL/PALISADE as bac…
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
[ICML'23 Oral] HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption
MedBlindTuner: Towards Privacy-preserving Fine-tuning on Biomedical Images with Transformers and Fully Homomorphic Encryption
Examples for HElayers homomorphic encryption SDK for C++ and Python
Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.
The repo of "BumbleBee: Secure Two-party Inference Framework for Large Transformers" (NDSS 2025)
A framework for Privacy Preserving Machine Learning
Non-interactive protocol for secure transformer inference based on RNS-CKKS.
IBM HElayers homomorphic encryption SDK for C++ and Python
[ICLR 2022] Official implementation of cosformer-attention in cosFormer: Rethinking Softmax in Attention
Official implementation for AutoFHE: Automated Adaption of CNNs for Efficient Evaluation over FHE. The paper is presented at the 33rd USENIX Security Symposium, 2024.
A re-implementation of the "Extracting Training Data from Large Language Models" paper by Carlini et al., 2020
Privacy Meter: An open-source library to audit data privacy in statistical and machine learning algorithms.
Official Code Implementation for the CCS 2022 Paper "On the Privacy Risks of Cell-Based NAS Architectures"
[NeurIPS 2022] Implementation of "AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition"
TAOISM: A TEE-based Confidential Heterogeneous Deployment Framework for DNN Models
Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
Goten: GPU-Outsourcing Trusted Execution of Neural Network Training and Prediction
Source code accompanying our CVPR 2019 paper: "NetTailor: Tuning the architecture, not just the weights."
A VHDL IP for ECC (Elliptic Curve Cryptography) hardware acceleration
🎲 A Tiny and Platform-Independent True Random Number Generator for any FPGA (and ASIC).
Garbled Assembly with RAM in the paper "Towards Generic MPC Compilers via Variable Instruction Set Architectures (VISAs)"