Secure Outsourced Matrix Computation and Application to Neural Networks
科学 数学 人工智能 计算
更多相关阅读
- Secure Computation
- Flexible and Efficient Verifiable Computation on Encrypted Data
- Maliciously Secure Matrix Multiplication with Applications to Private Deep Learn
- Efficiently Verifying Outsourced Cloud Computation：from Theory to Practice
- Shusen Wang -- Matrix Sketching for Secure Federated Learning
- Two-round n-out-of-n and Multi-Signatures and Trapdoor Commitment from Lattice
- Efficient Homomorphic Comparison Methods with Optimal Complexity
- Faster Bootstrapping with Polynomial Error
- Lattice-Based Crypto
- DeepMind x UCL 报告
- Secure and Privacy - Preserving Data Analytics and Machine Learning
- Vitalik Buterin - Exploring fully homomorphic encryption (FHE)
- Lattices_ from geometry to cryptography - Oded Regev
- Multi-Key Homomorphic Encryption with Packed Ciphertexts
- Oded Regev (NYU)_ Continuous LWE and robust machine learning
- A Low Complexity Decentralized Neural Net with Centralized Equivalence using Lay
- Gladius: LWR based efficient hybrid public key encryption with distributed decry
- The CKKS (a.k.a. HEAAN) FHE Scheme
- Theory and Practice of Multi-Party Computation Workshop (TPMPC) 2020
- Phong Nguyen - Lattice-Based Cryptography
