Niffler: A Context-Aware and User-Independent Side-Channel Attack System for Password Inference

Niffler: A Context-Aware and User-Independent Side-Channel Attack System for Password Inference
复制标题

Niffler:用于密码推断的上下文感知且独立于用户的侧通道攻击系统

DOI:
10.1155/2018/4627108
复制
发表时间:
2018-05
期刊:
Wireless Communications and Mobile Computing (CCF C类期刊)
影响因子:
--
通讯作者:
Wang Lina
Wang Lina
中科院分区:
其他
文献类型:
--
作者:
Tang Benxiao;Wang Zhibo;Wang Run;Zhao Lei;Wang Lina

文献摘要

参考文献

相似文献

数字密码锁已成为移动设备常用的主要认证方式。研究表明,嵌入在移动设备上的传感器可以用来推断密码。然而,现有的工作要么集中在单个按键推理上,要么集中在整个密码序列推理上,这是依赖于用户的,并且需要花费大量的精力来收集地面真值训练数据。在本文中,我们设计了一种新的侧信道攻击系统,称为嗅嗅,它利用用户独立的连续点击按钮的运动特征来推断智能手机上的解锁密码。我们提取角度特征来反映变化趋势,并结合动态时间规整算法构建多类别分类器来推断每次运动的概率。我们进一步使用马尔可夫模型来建模解锁过程,并使用具有最高概率的序列作为攻击候选。此外,将成功攻击的传感器读数进一步反馈,不断提高分类器的准确率。在我们的实验中,从25个参与者中收集了10万个样本来评估嗅嗅的性能。结果表明,在用户独立和用户依赖的训练样本较少的环境下,Niffler分别在10次尝试后达到70%和85%的准确率。
Digital password lock has been commonly used on mobile devices as the primary authentication method. Researches have demonstrated that sensors embedded on mobile devices can be employed to infer the password. However, existing works focus on either each single keystroke inference or entire password sequence inference, which are user-dependent and require huge efforts to collect the ground truth training data. In this paper, we design a novel side-channel attack system, called Niffler, which leverages the user-independent features of movements of tapping consecutive buttons to infer unlocking passwords on smartphones. We extract angle features to reflect the changing trends and build a multicategory classifier combining the dynamic time warping algorithm to infer the probability of each movement. We further use the Markov model to model the unlocking process and use the sequences with the highest probabilities as the attack candidates. Moreover, the sensor readings of successful attacks will be further fed back to continually improve the accuracy of the classifier. In our experiments, 100,000 samples collected from 25 participants are used to evaluate the performance of Niffler. The results show that Niffler achieves 70% and 85% accuracy with 10 attempts in user-independent and user-dependent environments with few training samples, respectively.
通过智能手机上的运动传感器行为分析进行输入提取
DOI: 10.1016/j.cose.2015.06.013
发表时间: 2015-09
影响因子: 5.6
作者:
Shen Chao;Pei Shichao;Yang Zhenyu;Guan Xiaohong
通讯作者: Guan Xiaohong
DOI: 10.1145/2046707.2046769
发表时间: 2011-10
期刊: --
影响因子: --
作者:
R. Raguram;A. M. White;D. Goswami;F. Monrose;Jan-Michael Frahm
通讯作者: R. Raguram;A. M. White;D. Goswami;F. Monrose;Jan-Michael Frahm
DOI: 10.1145/2897845.2897897
发表时间: 2016-05
期刊: Proceedings of the 11th ACM on Asia Conference on Computer and Communications Security
影响因子: --
作者:
Lingyun Ying;Yao Cheng;Yemian Lu;Yacong Gu;Purui Su;D. Feng
通讯作者: Lingyun Ying;Yao Cheng;Yemian Lu;Yacong Gu;Purui Su;D. Feng
DOI: 10.1145/2516760.2516770
发表时间: 2013-11
期刊: --
影响因子: --
作者:
Laurent Simon;Ross J. Anderson
通讯作者: Laurent Simon;Ross J. Anderson
DOI: 10.14722/ndss.2016.23390
发表时间: 2016
期刊: --
影响因子: --
作者:
Anupam Das;N. Borisov;M. Caesar
通讯作者: Anupam Das;N. Borisov;M. Caesar