用同态加密技术让AI处理加密数据，还能降低错误率
Arbitrary Reduction of Validation Error for AI Decision Tests using Homomorphic AI and Repetition Codes
- 用可保留相似性的哈希加密方法处理数据，不改原有AI模型
- 压缩率提升10倍，计算时间和能耗同步下降
- 通过纠错码可任意减少AI决策的验证误差，适合高可靠场景
本文基于哈希同态人工智能（HbHAI）技术，提出一种新型依赖密钥的哈希函数，天然保持大多数人工智能算法依赖的相似性特性。该方法可在加密数据上直接使用现有原生AI算法，无需修改，性能远超现有同态加密方案，甚至优于明文数据处理。主要成果有二：其一，压缩率最高降低至1/10，显著提升大规模数据处理效率，同时降低计算时间与能耗；其二，通过引入重复纠错码，可任意减小基于AI决策测试的最终验证误差。
原文摘要 · Abstract (English)
This paper presents new results and breakthrough obtained with the HbHAI techniques (Hash-based Homomorphic Artificial Intelligence) proposed in \cite{filiol0,sepp}. HbHAI is based on a novel class of key-dependent hash functions that naturally preserve most similarity properties, most AI algorithms rely on. It enables to analyse and process data in its cryptographically secure form while using existing native AI algorithms without modification, with unprecedented performances compared to existing homomorphic encryption schemes and most notably compared to the same processing on corresponding plaintext data. Two major results have been obtained further. First we enable to reduce the compression rate up to a factor of 10 thus allowing to process massive datasets while reducing the computation time and the energy footprint in the same order. Second, we show how it is possible to arbitrarily reduce the final validation error of AI-based decision tests by using repetition error-correcting codes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。