基于MILP的MGFN全轮差分分析及改进  

Differential analysis and improvement of full-round MGFN based on MILP

作　　者：李艳俊 毕鑫杰 项勇 林怡平 Li Yanjun;Bi Xinjie;Xiang Yong;Lin Yiping(Information Industry Information Security Evaluation Center,The 15th Research Institute of China Electronics Technology Group Corporation,Beijing 100083,China;Dept.of Cryptologic Science&Technology,Beijing Institute of Electronic Science&Technology,Beijing 100070,China;Dept.of Cyberspace Security,Beijing Institute of Electronic Science&Technology,Beijing 100070,China)

机构地区：[1]中国电子科技集团公司第十五研究所信息产业信息安全测评中心,北京100083 [2]北京电子科技学院密码科学与技术系,北京100070 [3]北京电子科技学院网络空间安全系,北京100070

出　　处：《计算机应用研究》2024年第3期911-915,922,共6页Application Research of Computers

基　　金：北京市自然科学基金资助项目(4234084)。

摘　　要：研究了轻量级分组密码MGFN算法的抗差分分析能力并提出了改进方法。首先,基于MILP工具对MGFN算法建模,搜索迭代差分并构造了全轮差分路径,整体差分概率为2-40,远远大于随机置换的差分概率。然后,给出S盒的差分分支数概念并将其作为衡量差分安全性的指标,以新S盒替代原MGFN算法的S盒,并修改了密钥扩展算法,提出新的MGFN-P算法。最后,通过差分路径搜索和分析比较,说明了MGFN-P算法比原MGFN算法更安全、高效。This article investigated the MGFN algorithm’s ability to resist differential analysis and proposed improved methods.First of all,it modeled this algorithm based on the MILP,and then got a 6-round iterative differential and a full round differential path with a total probability of 2-40,which was much larger than the differential probability of random permutation.Secondly,it gave the branch number of the S-box as an indicator to measure its differential safety.This paper also replaced the S-box of MGFN algorithm with a new S-box and proposed a new MGFN-P algorithm by modifying the key extension algorithm.Finally,differential path search and analysis show that MGFN-P algorithm is more secure and efficient than the original algorithm.

关 键 词：MGFN 轻量级分组密码 MILP 差分分析 分支数 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]