基于深度学习的多差分神经网络区分器及其应用  

Multi Differential Attack Based on Deep Learning and Its Application

作　　者：段明 付超辉 魏强[1] 吴茜琼 周睿[1] DUAN Ming;FU Chaohui;WEI Qiang;WU Qianqiong;ZHOU Rui(Information Engineering University,Zhengzhou 450001,China)

机构地区：[1]信息工程大学,河南郑州450001

出　　处：《信息工程大学学报》2021年第3期347-350,共4页Journal of Information Engineering University

基　　金：河南省自然科学基金计划资助项目(212300410420)。

摘　　要：随着深度学习的发展,尤其是随着多层神经网络(MLP)、深度神经网络(DNN)、卷积神经网络(CNN)等网络的出现,其在多个领域得到广泛应用,如视觉识别、语音识别、自然语言处理等领域。在2019年的美密会上提出利用单差分深度残差网络区分器进行密钥恢复攻击的方法,将深度学习的应用扩展到密码算法分析领域。利用多差分残差网络区分器进行密钥恢复攻击,该方法可有效减少数据复杂度,并增加攻击轮数。以RC516的攻击为例,计算复杂度和数据复杂度分别减少为后者的1/12,攻击轮数由11个半轮增加到了12个半轮。With the emergence of MLP,DNN,CNN and other networks particularly,deep learning has been widely used in many domains,such as visual recognition,speech recognition,natural language processing and other domains.A key recovery attack method using a single differential deep residual network distinguisher is proposed in CRYPTO2019,which extended the application of deep learning to the analysis of cryptographic algorithm.A key recovery method using multi differential residual network distinguisher is proposed.This method can effectively reduce the data complexity and increase the number of attack rounds.Taking RC516 attack as an example,the computational complexity and data complexity are reduced to 1/12 of the latter,and the number of attack rounds is increased from 11 half-round to 12 half-round.

关 键 词：深度学习 密码算法分析 差分分析 多差分神经网络区分器 RC5 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]