典型文献
Deep-learning-based cryptanalysis of two types of nonlinear optical cryptosystems
文献摘要：
The two types of nonlinear optical cryptosystems(NOCs)that are respectively based on amplitude-phase retrieval algorithm(APRA)and phase retrieval algorithm(PRA)have attracted a lot of attention due to their unique mechanism of encryption process and remarkable ability to resist common attacks.In this paper,the securities of the two types of NOCs are evaluated by using a deep-learning(DL)method,where an end-to-end densely connected convolutional network(DenseNet)model for cryptanalysis is developed.The proposed DL-based method is able to retrieve unknown plaintexts from the given ciphertexts by using the trained DenseNet model without prior knowledge of any public or private key.The results of numerical experiments with the DenseNet model clearly demonstrate the validity and good performance of the proposed the DL-based attack on NOCs.
文献关键词：
中图分类号：
作者姓名：
Xiao-Gang Wang;Hao-Yu Wei
作者机构：
Department of Applied Physics,Zhejiang University of Science and Technology,Hangzhou 310023,China;Department of Optical Engineering,Zhejiang A&F University,Hangzhou 311300,China
文献出处：
引用格式：
[1]Xiao-Gang Wang;Hao-Yu Wei-.Deep-learning-based cryptanalysis of two types of nonlinear optical cryptosystems)[J].中国物理B（英文版）,2022(09):328-335
A类：
NOCs,APRA,plaintexts
B类：
Deep,learning,cryptanalysis,types,nonlinear,optical,cryptosystems,that,are,respectively,amplitude,phase,retrieval,algorithm,have,attracted,lot,attention,due,their,unique,mechanism,encryption,process,remarkable,ability,resist,common,attacks,In,this,paper,securities,evaluated,by,using,deep,DL,method,where,end,densely,connected,convolutional,network,DenseNet,model,developed,proposed,retrieve,unknown,from,given,ciphertexts,trained,without,prior,knowledge,any,public,private,key,results,numerical,experiments,clearly,demonstrate,validity,good,performance
AB值：
0.55006
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
