Efficient FHE-based privacy-enhanced neural network for trustworthy AI-as-a-service

• Main Authors: Lam, Kwok-Yan, Lu, Xianhui, Zhang, Linru, Wang, Xiangning, Wang, Huaxiong, Goh, Si Qi
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Fully homomorphic encryption; Privacy-enhanced neural networks; Look-up table algorithm; Deep neural network; Digital trust; Secure cloud computing; Data privacy; Cryptographic protocol; Applied cryptography
• Online Access: https://hdl.handle.net/10356/174567
• Institution: Nanyang Technological University

AI-as-a-Service has emerged as an important trend for supporting the growth of the digital economy. Digital service providers make use of their vast amount of customer data to train AI models (such as image recognition, financial modelling and pandemic modelling etc) and offer them as a service on t...