• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Arabian Journal for Science and Engineering >Fingerprint Spoofing Detection to Improve Customer Security in Mobile Financial Applications Using Deep Learning
【24h】

Fingerprint Spoofing Detection to Improve Customer Security in Mobile Financial Applications Using Deep Learning

机译：使用深度学习的指纹欺骗检测可提高移动金融应用程序中的客户安全性

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Online banking and financial services using mobile applications are seeing a persistent growth among customers, who areusing these for their financial transactions. This rise in the use of such applications in smart devices has increased securityconcerns. There is need for secure mechanisms to prevent fraud and protect personal information. This paper investigates theuse of biometric identification in banking and financial services, which leverage the use of smartphones and tablets. Whilecustomer engagement and brand loyalty are important concerns, these services are making use of biometric authentication tomake customer interactions more secure. However, as technology is growing rapidly, spoofing attacks are becoming common.In this paper, authors have proposed a robust framework to detect spoofing attacks in fingerprint recognition. The processof spoofing detection involves contrast enhancement using histogram equalization and a deep convolutional neural networkarchitecture. Authors have validated the results on various biometric spoofing benchmarks, each one containing real andspoofed samples of user fingerprints. The results indicate that our proposed framework performs better as evaluated againstother existing pre-trained CNN models and state-of-the-art methods.
机译：使用移动应用程序的在线银行和金融服务在客户中持续增长，他们将这些用于金融交易。在智能设备中使用此类应用程序的这种增加增加了对安全性的担忧。需要安全的机制来防止欺诈和保护个人信息。本文研究了在银行和金融服务中利用生物识别技术的情况，这些技术利用了智能手机和平板电脑的使用。尽管客户参与度和品牌忠诚度是重要的考虑因素，但这些服务正在利用生物识别技术来使客户交互更加安全。但是，随着技术的飞速发展，欺骗攻击正变得越来越普遍。在本文中，作者提出了一个强大的框架来检测指纹识别中的欺骗攻击。欺骗检测的过程涉及使用直方图均衡和深度卷积神经网络体系结构进行对比度增强。作者已经在各种生物特征欺骗基准上验证了结果，每个基准都包含真实的和伪造的用户指纹样本。结果表明，与其他现有的预训练CNN模型和最新方法相比，我们提出的框架具有更好的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号