DOI: 10.11992/tis.201712006
网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.TP.20180410.1436.020.html
PG-RNN: 一种基于递归神经网络的密码猜测模型
滕南君
1,2
,鲁华祥
1,3,4
,金敏
1
,叶俊彬
1,2
,李志远
1,2
(1. 中国科学院 半导体研究所,北京 100083; 2. 中国科学院大学,北京 100089; 3. 中国科学院 脑科学与智能技
术卓越创新中心,上海 200031; 4. 半导体神经网络智能感知与计算技术北京市重点实验室,北京 100083)
摘 要:用户名—密码(口令)是目前最流行的用户身份认证方式,鉴于获取真实的大规模密码明文非常困难,
利用密码猜测技术来生成大规模密码集,可以评估密码猜测算法效率、检测现有用户密码保护机制的缺陷等,
是研究密码安全性的主要方法。本文提出了一种基于递归神经网络的密码猜测概率模型(password guessing
RNN, PG-RNN),区别于传统的基于人为设计规则的密码生成方法,递归神经网络能够自动地学习到密码集本
身的分布特征和字符规律。因此,在泄露的真实用户密码集上训练后的递归神经网络,能够生成非常接近训练
集真实数据的密码,避免了人为设定规则来破译密码的局限性。实验结果表明,PG-RNN生成的密码在结构字
符类型、密码长度分布上比Markov模型更好地接近原始训练数据的分布特征,同时在真实密码匹配度上,本文
提出的PG-RNN模型比目前较好的基于生成对抗网络的PassGAN模型提高了1.2%。
关键词:密码生成;深度学习;递归神经网络;Markov;密码猜测
中图分类号:TP391 文献标志码:A 文章编号:1673−4785(2018)06−0889−08
中文引用格式:滕南君, 鲁华祥, 金敏, 等. PG-RNN: 一种基于递归神经网络的密码猜测模型[J]. 智能系统学报, 2018, 13(6):
889–896.
英文引用格式:TENG Nanjun, LU Huaxiang, JIN Min, et al. PG-RNN: a password-guessing model based on recurrent neural net-
works[J]. CAAI transactions on intelligent systems, 2018, 13(6): 889–896.
PG-RNN: a password-guessing model based on recurrent neural networks
TENG Nanjun
1,2
,LU Huaxiang
1,3,4
,JIN Min
1
,YE Junbin
1,2
,LI Zhiyuan
1,2
(1. Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China; 2. University of Chinese Academy of Sci-
ences, Beijing 100089, China; 3. Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences,
Shanghai 200031, China; 4. Semiconductor Neural Network Intelligent Perception and Computing Technology Beijing Key Lab,
Beijing 100083, China)
Abstract: Passwords are the most popular way of user ID authentication. However, it is rather difficult to obtain large-
scale real text passwords. Generating large-scale password sets based on password-guessing techniques is a principal
method to research password security, which can be applied to evaluate the efficiency of password-guessing algorithm
and detect the defects of existing user-password protective mechanisms. In this paper, we propose a password guessing-
based recurrent neural network (PG-RNN) model. Our model can directly and automatically infer the distribution char-
acteristics and character rules from the data of password sets, which is different from the traditional password generat-
ing method based on manual design rule. Therefore, an RNN model that has been trained on a disclosed real user pass-
word set can generate passwords very close to the real data of the training set, which avoids the limitations of manual
setting for password guessing. The results of our experiments show that PG-RNN can generate passwords closer to
primitive data distribution more than Markov in password length and character structure categories. When evaluating on
large password dataset, the proposed PG-RNN model matching outperforms that of PassGAN, which is based on gener-
ative adversarial networks, by more than 1.2%.
Keywords: password generation; deep learning; recurrent neural networks; Markov; password guessing
在网络时代普及的今天,密码是一种被广泛
使用的用户验证方法。主要原因在于,一方面密
码方便理解、使用,另一方面较容易实现。然而,
收稿日期:2017−12−05. 网络出版日期:2018−04−10.
基金项目:北京市科技计划课题(Z171100002217094);中科院战
略性先导科技专项(A类)(XDA18040400).
通信作者:金敏. E-mail:jinmin08@semi.ac.cn.
第 13 卷第 6 期
智 能 系 统 学 报
Vol.13 No.6
2018 年 12 月
CAAI Transactions on Intelligent Systems
Dec. 2018
评论0