Homomorphic Encryption
An encryption technique that allows computations to be performed directly on ciphertext without decrypting the data, theoretically achieving the highest level of data privacy protection. However, its computational overhead remains substantial, and it has not yet been widely adopted in production-grade AI inference.
Core Facts
Timeline (last 90 days)
Privacy-enhancing technologies (PETs) include homomorphic encryption, federated learning, differential privacy and secure multi-party computation, with the goal of maintaining privacy protection at the data usage stage as well, but they still face deployment challenges such as high performance overhead and high engineering complexity.
In actual products, the combination of TEE and traditional encryption is more practically feasible than homomorphic encryption.
Traditional multi-party computation (MPC) is implemented through cryptographic protocols such as secret sharing and homomorphic encryption, but the computational overhead is enormous, making it difficult to apply to large-scale neural network inference.
Homomorphic encryption theoretically allows inference to be run directly on encrypted data, but the computational overhead is still too large and it has not yet become practical.
同态加密可以在加密数据上直接进行计算，而无需先解密，计算结果同样是加密的，只有持有密钥的人才能解密
谷歌近期推动同态加密技术，目标是让同态加密变得实用，通过算法优化、硬件加速和开发工具链完善来压缩性能开销
同态加密的理论基础可以追溯到2009年Craig Gentry的工作，他基于理想格数学结构首次证明了可以在密文上执行任意计算
CKKS方案支持近似浮点数运算，特别适合机器学习中的矩阵乘法和激活函数计算，成为AI领域应用同态加密的重要基础
在密文上做运算的计算量往往是明文运算的成千上万倍，是同态加密工程化的最大障碍
All Facts (9)
Homomorphic encryption theoretically allows inference to be run directly on encrypted data, but the computational overhead is still too large and it has not yet become practical.
80%UnverifiedPrivacy-enhancing technologies (PETs) include homomorphic encryption, federated learning, differential privacy and secure multi-party computation, with the goal of maintaining privacy protection at the data usage stage as well, but they still face deployment challenges such as high performance overhead and high engineering complexity.
50%UnverifiedIn actual products, the combination of TEE and traditional encryption is more practically feasible than homomorphic encryption.
50%UnverifiedTraditional multi-party computation (MPC) is implemented through cryptographic protocols such as secret sharing and homomorphic encryption, but the computational overhead is enormous, making it difficult to apply to large-scale neural network inference.
50%Unverified同态加密可以在加密数据上直接进行计算，而无需先解密，计算结果同样是加密的，只有持有密钥的人才能解密
50%Unverified同态加密的理论基础可以追溯到2009年Craig Gentry的工作，他基于理想格数学结构首次证明了可以在密文上执行任意计算
50%UnverifiedCKKS方案支持近似浮点数运算，特别适合机器学习中的矩阵乘法和激活函数计算，成为AI领域应用同态加密的重要基础
50%Unverified在密文上做运算的计算量往往是明文运算的成千上万倍，是同态加密工程化的最大障碍
50%Unverified谷歌近期推动同态加密技术，目标是让同态加密变得实用，通过算法优化、硬件加速和开发工具链完善来压缩性能开销
50%