基于运动物体识别的三维动态验证码设计  

CAPTCHA Design Based on Moving Object Recognition

作　　者：崔竞松[1] 王丽婧[1] 

机构地区：[1]武汉大学计算机学院,湖北武汉430072

出　　处：《信息安全与通信保密》2010年第4期65-67,共3页Information Security and Communications Privacy

基　　金：国家自然科学基金资助项目(批准号:60603012;60703009;90718006);国家863计划资助项目(编号:2008AA01Z404)

摘　　要：基于OCR难题的平面静态可视化验证码以其在实现和操作方面的优势成为了目前CAPTCHA技术应用的主流形式。然而,随着各种有针对性的文字分割技术的出现,这种基于OCR难题的验证码的安全性受到越来越严重的威胁,用这种方法所保护的网络服务系统正在越来越多地被bots程序攻击。目前迫切需要一种既能够提高验证码的安全性,又能够保持实用性的新型CAPTCHA验证码。该课题拟在运动对象识别难题上,构建一种动画验证码,使得攻击者只有在有效解决运动对象识别难题后,才能通过该动画验证码的测试进而登录服务系统。该课题所提出的设计思路将会在CAPTCHA研究领域开辟一个新的研究方向。此类动画验证码将能够杜绝所有静态OCR技术的攻击,并能够抵抗过去所有的对于运动物体检测的攻击。CAPTCHA is a test that could automatically tell humans from computer programs. This allows the server to identify that the visitor is a human or a computer, and only to provide services to humans, thus improving the security of current server system and user information. The static plane visual CAPTCHA based on OCR problems and with the advantages of implementation and operation has become the mainstream of the current CAPTCHA technology application. However, with a variety of targeted text segmentation technologies, such a verification code based on OCR problems is faced with increasing security threats. In this paper, a new CAPTCHA based on moving object identification and tracking problems is proposed, which is referred to biological motion vision model. An Innovative single-frame zeroknowledge rule is also put forward to make the code generation algorithm based on Edge mutation. An attacker could log on the test service system only after he solves the moving object recognition problem. Such animation code could be able to resist the attacks of all the static OCR technology, including the mainstream of attacks against the moving object detection.

关 键 词：边缘突变 运动物体识别 单帧零知识 CAPTCHA 网络安全 

分 类 号：TP393.08[自动化与计算机技术—计算机应用技术]