网上银行验证码研究与安全性分析  

Research and Security Analysis of Online Banking CAPTCHA

作　　者：冯杰[1] 李旭伟[1] 

机构地区：[1]四川大学计算机学院,四川成都610065

出　　处：《计算机技术与发展》2013年第11期144-147,160,共5页Computer Technology and Development

基　　金：国家"863"高技术发展计划项目子课题(2002AA144020)

摘　　要：验证码(CAPTCHA),是用于区别用户是人类还是机器的一种计算机自动程序。作为一种辅助手段,验证码在互联网安全领域扮演着很重要的角色。为了对网上银行验证码进行安全性评价,其过程包括三方面:验证码图像采集、图像预处理和图像识别。对国内网上银行验证码特点进行分析,采用最具可靠性的BP神经网络算法,选取其中具有代表性的验证码进行训练、识别。从识别结果中分析,通过所得到的识别率来评价国内网上银行验证码的安全有效性,并对网上银行验证码的生成给出一定的建议。CAPTCHA is an automatic computer program that determines a user is a human or a computer. As a supplementary measure, CAPTCHA plays a very important role in Internet security. In order to evaluate the safety of the online banking CAFTCHA, its process consists of three main areas, CAPTCHA image acquisition, image pre-processing and image recognition. Analyze the characteristics of domestic online banking CAPTCHA code,and then use the most reliable BP neural network algorithm to select the representative codes into training and identifying. From the recognition result of analysis, evaluate the safety and effectiveness of the domestic online banking CAPTCHA code, and give some suggestions to online banking CAPTCHA code generated by the obtained recognition rate.

关 键 词：验证码 预处理 BP神经网络 网上银行 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]