当前位置: X-MOL 学术Comput. Electr. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
CMOS technology-based energy efficient artificial neural session key synchronization for securing IoT
Computers & Electrical Engineering ( IF 4.0 ) Pub Date : 2021-08-25 , DOI: 10.1016/j.compeleceng.2021.107369
Arindam Sarkar 1 , Mohammad Zubair Khan 2 , Abdulfattah Noorwali 3
Affiliation  

In this paper, CMOS technology-based neural session key generation is proposed for integration with the Internet-of-Things (IoT) to enhancing security. Recent technological developments in the IoT era enable improved strategies to exacerbate the maintenance of energy efficiency and stability issues. The existing security solutions do not properly address IoT’s security. A small logic area ASIC implementation of a re-keying enabled Triple Layer Vector-Valued Neural Network (TLVVNN) using CMOS architectures with measurements of 65 and 130 nanometers are proposed for integration with IoT. The paper aims to defend IoT devices using TLVVNN synchronization to enhance security. For a 20% weight misalignment in the re-keying phase, the synchronization period may be decreased from 1.25 ms to less than 0.7 ms, according to behavioral simulations. Experiments to verify the proposed technique’s performance are conducted, and the findings demonstrate that the proposed method has greater performance benefits than the existing related techniques.



中文翻译:

用于保护物联网的基于 CMOS 技术的节能人工神经会话密钥同步

在本文中,提出了基于 CMOS 技术的神经会话密钥生成,以与物联网 (IoT) 集成以增强安全性。物联网时代的最新技术发展使改进策略能够加剧能源效率和稳定性问题的维护。现有的安全解决方案没有正确解决物联网的安全问题。建议使用具有 65 和 130 纳米测量值的 CMOS 架构的重新键控启用三层矢量值神经网络 (TLVVNN) 的小型逻辑区域 ASIC 实现与物联网集成。本文旨在使用 TLVVNN 同步来保护 IoT 设备以增强安全性。根据行为模拟,对于重新键入阶段中 20% 的权重未对准,同步周期可以从 1.25 毫秒减少到小于 0.7 毫秒。

更新日期:2021-08-25
down
wechat
bug