引用本文: |
-
邓浩然,王春琦,杨程,等.基于深度学习的多密码适配轻量级密码差分分析算法[J].电讯技术,2025,65(7):1069 - 1077. [点击复制]
- DENG Haoran,WANG Chunqi,YANG Cheng,et al.A Deep Learning-based Lightweight Cryptographic Differential Analysis Algorithm for Multi-cipher Adaptation[J].,2025,65(7):1069 - 1077. [点击复制]
|
|
摘要: |
在资源受限的物联网设备上,针对基于深度学习的传统差分密码分析方法中模型仅能适配单一密码的局限性,提出了一种基于深度学习的多密码适配轻量级密码差分分析算法。通过引入两种独特的数据输入机制,使得算法能够同时处理多种类型的密码数据,大大增强了其通用性。同时,通过引入全新的密钥恢复算法参数调整策略,使得模型在一次训练后能灵活对多种轻量级密码进行差分分析。此外,算法支持对不同密码间的相似性及交替加密的安全性进行定量分析,这是传统算法所不具备的。实验结果表明,相较于传统方法,所提算法在不同密码间的泛化性能和密钥恢复准确率上均有显著提升,最高提升幅度达 2.1%。这一成果为未来通信中的数据安全保护提供了一种高效的分析与评估策略,有望在资源受限的物联网设备安全防护中发挥重要作用。 |
关键词: 物联网设备 安全防护 深度学习 轻量级密码 差分分析 多密码适配 |
DOI:10.20079/j.issn.1001-893x.241118005 |
|
基金项目: |
|
A Deep Learning-based Lightweight Cryptographic Differential Analysis Algorithm for Multi-cipher Adaptation |
DENG Haoran,WANG Chunqi,YANG Cheng,DONG Feifei,CHEN Tonghai |
(1.Chengdu Monitoring Station of National Radio Monitoring Center,Chengdu 611130;2.College of Electronic and Information Engineering,Nanjing University of Aeronautics and Astronautics,Nanjing 210016) |
Abstract: |
For resource-constrained Internet of Things(IoT) devices,in view of the limitation of traditional deep learning-based differential cryptanalysis methods,where the model can only be adapted to a single cipher,a deep learning-based differential cryptanalysis algorithm for multi-cipher adaptation of lightweight ciphers is proposed. |
Key words: Internet of Things device security protection deep learning lightweight cipher differential cryptanalysis multi-cipher adaptability |