Treadmill attack on gait-based authentication systems
Treadmill attack on gait-based authentication systems
复制标题
对基于步态的身份验证系统的跑步机攻击
DOI：
10.1109/btas.2015.7358801
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
A. Jain
中科院分区：
文献类型：
--
作者：
R. Kumar;V. Phoha;A. Jain
在本文中，我们证明了可以在数字跑步机的支持下模仿通过智能手机加速度计捕获的个人步态模式。此外，我们为基于基线步态的身份验证系统（GBAS）设计了一种攻击，并在 18 个用户数据集上严格测试其性能。通过仅使用两个模仿器并使用具有速度控制功能的简单数字跑步机，该攻击将随机森林（我们实验中性能最佳的分类器）的平均错误接受率 (FAR) 从 5.8% 提高到 43.66%。更具体地说，18 个用户中有 11 个的 FAR 增加到 70% 或更多。我们的结果要求重新审视 GBAS 的设计，以使其能够抵御此类攻击。
In this paper, we demonstrate that gait patterns of an individual captured through a smartphone accelerometer can be imitated with the support of a digital treadmill. Furthermore, we design an attack for a baseline gait based authentication system (GBAS) and rigorously test its performance over an eighteen user data-set. By employing only two imitators and using a simple digital treadmill with speed control functionality, the attack increases the average false acceptance rate (FAR) from 5.8% to 43.66% for random forest, the best performing classifier in our experiments. More specifically, the FAR of eleven out of eighteen users increased to 70% or more. Our results call for a revisit of the design of the GBAS to make them resilient to such attacks.