Deployment of Keystroke Analysis on a Smartphone
Deployment of Keystroke Analysis on a Smartphone
复制标题
DOI：
10.4225/75/57b55a56b876a
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
A. Buchoux;N. Clarke
中科院分区：
文献类型：
--
作者：
A. Buchoux;N. Clarke
移动的设备上的当前安全性通常限于个人识别码（PIN），这是一种基于秘密知识的技术，历史上已证明其不能有效地防止误用。不幸的是，随着移动的设备（如网上银行和购物）功能的不断增加，对更有效的保护的需求势在必行。这项研究提出了使用双因素身份验证作为一种增强技术，在智能手机上进行身份验证。通过利用秘密知识和故障分析，提出了一个更强大的更鲁棒的机制将存在。虽然使用移动的设备的指纹分析在实验研究中已被证明是有效的，但这些研究仅利用移动终端来捕获样本，而不是执行实际认证的更具计算挑战性的任务。鉴于有限的处理能力的移动的设备，本研究的重点是部署一个移动终端，利用众多的模式分类器的分析。考虑到计算与性能的权衡，结果表明统计分类器是最有效的。
The current security on mobile devices is often limited to the Personal Identification Number (PIN), a secretknowledge based technique that has historically demonstrated to provide ineffective protection from misuse. Unfortunately, with the increasing capabilities of mobile devices, such as online banking and shopping, the need for more effective protection is imperative. This study proposes the use of two-factor authentication as an enhanced technique for authentication on a Smartphone. Through utilising secret-knowledge and keystroke analysis, it is proposed a stronger more robust mechanism will exist. Whilst keystroke analysis using mobile devices have been proven effective in experimental studies, these studies have only utilised the mobile device for capturing samples rather than the more computationally challenging task of performing the actual authentication. Given the limited processing capabilities of mobile devices, this study focuses upon deploying keystroke analysis to a mobile device utilising numerous pattern classifiers. Given the trade-off with computation versus performance, the results demonstrate that the statistical classifiers are the most effective.