Input Biometric System Design for Handheld Devices

The development of networks, especially the Internet, is changing the way we do computing. The addition of multiple devices, such as smartphones and tablets, gives us new ways to access information, but at the same time makes sensitive information more prone to be lost or used by unauthorized users. In an effort to respond to those new threats, keystroke biometrics is an area being extensively studied for continuously authenticating users on those devices. Keystroke biometrics is a promising solution that will help guarantee the security of sensitive information and device access. It uses the keyboard only and is invisible to the user. Keystroke biometrics takes advantage of the natural style and rhythm in which a user inputs characters on a soft or hard keyboard. Keystroke rhythms, area covered on a soft keyboard for a particular key, and timing can be measured to build a biometric pattern for identification and authentication. This paper describes user interaction with a touch screen device using a soft keyboard and the data that can be mined from a soft keyboard. We present the structure and technical details of our biometric keyboard for the Android platform and our data collection process in our test cases.

网络的发展，尤其是互联网，正在改变我们进行计算的方式。多种设备的增加，比如智能手机和平板电脑，为我们提供了获取信息的新途径，但同时也使敏感信息更容易丢失或被未经授权的用户使用。为了应对这些新的威胁，击键生物识别是一个正在被广泛研究的领域，用于在这些设备上对用户进行持续认证。击键生物识别是一种很有前景的解决方案，它将有助于保障敏感信息和设备访问的安全。它仅使用键盘，且对用户不可见。击键生物识别利用了用户在软键盘或硬键盘上输入字符的自然风格和节奏。击键节奏、在软键盘上特定按键所覆盖的区域以及时间都可以被测量，以构建用于识别和认证的生物识别模式。本文描述了用户使用软键盘与触摸屏设备的交互以及可以从软键盘挖掘的数据。我们介绍了我们用于安卓平台的生物识别键盘的结构和技术细节，以及我们在测试案例中的数据收集过程。