基于声音空间梯度的高稳健性击键识别方法

doi:10.11959/j.issn.1000-436x.2020095

通信学报 ›› 2020, Vol. 41 ›› Issue (5): 96-103.doi: 10.11959/j.issn.1000-436x.2020095

基于声音空间梯度的高稳健性击键识别方法

刘影¹,韩康康²,钱志鸿³

¹ 辽宁工程技术大学电子与信息工程学院，辽宁葫芦岛 125105
² 北京邮电大学电子工程学院，北京 100876
³ 吉林大学通信工程学院，吉林长春 130022

修回日期:2020-03-24 出版日期:2020-05-25 发布日期:2020-05-30
作者简介:刘影（1983- ），女，吉林大安人，博士，辽宁工程技术大学副教授，主要研究方向为无线定位、智能无线感知|韩康康（1997- ），男，河南商丘人，北京邮电大学硕士生，主要研究方向为认知无线电、智能信息处理|钱志鸿（1957- ），男，吉林长春人，博士，吉林大学教授、博士生导师，主要研究方向为基于物联网、D2D、Wi-Fi、RFID等的无线网络与通信技术
基金资助:
国家重点研发计划基金资助项目(2018YFB1403300);辽宁省教育厅一般项目资金资助项目(LJ2017QL013);辽宁省博士启动基金资助项目(20170520098);辽宁省自然科学基金资助项目(2019-ZD-0038);辽宁省创新人才支持计划基金资助项目(LR2016045)

High-roubustness keystroke recognition method based on acoustic spatial gradient

Ying LIU¹,Kangkang HAN²,Zhihong QIAN³

¹ School of Electronic and Information Engineering,Liaoning Technical University,Huludao 125105,China
² School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China
³ College of Communication Engineering,Jilin University,Changchun 130022,China

Revised:2020-03-24 Online:2020-05-25 Published:2020-05-30
Supported by:
The National Key Research and Development Program of China(2018YFB1403300);The Project of Educational Commission of Liaoning Province(LJ2017QL013);Liaoning Province Doctor Startup Fund(20170520098);The Natural Science Foundation of Liaoning Province(2019-ZD-0038);The Project of Innovative Talents Support of Liaoning Province(LR2016045)

摘要/Abstract

摘要：

针对声音信号受实际环境噪声影响引起耳蜗倒谱系数（CFCC）波动是导致击键内容识别率低的主要原因，研究相邻键CFCC之间的空间特征，建立基于点的CFCC空间梯度结构；在此基础上，在训练集和测试上研究CFCC空间梯度对击键内容识别的影响及确切邻域的点选取；最后，建立基于声音的高稳健性击键内容识别方法。在不同环境下进行的实验表明，所提CFCC空间梯度声音特征效果较好，识别准确率为96.15% 。

关键词: 击键检测, 声音识别, CFCC空间梯度, 神经网络

Abstract:

For the fluctuation of CFCC caused by environmental noise is the main reason for the low accuracy of keystroke detection,the spatial characteristics of adjacent between CFCC were studied,and the spatial gradient structure of CFCC based on points was established.On this basis,the effect of CFCC spatial gradient on keystroke content recognition and the selection of precise neighborhood points were studied on training and testing.Finally,a high-robustness keystroke recognition algorithm based on acoustic signals was constructed.Extensive experiments in different environments demonstrate that the proposed CFCC spatial gradient sound feature achieves great performance and the recognition accuracy is 96.15%.

Key words: keystroke detection, acoustic recognition, CFCC spatial gradient, neural network

中图分类号:

TP391

刘影,韩康康,钱志鸿. 基于声音空间梯度的高稳健性击键识别方法[J]. 通信学报, 2020, 41(5): 96-103.

Ying LIU,Kangkang HAN,Zhihong QIAN. High-roubustness keystroke recognition method based on acoustic spatial gradient[J]. Journal on Communications, 2020, 41(5): 96-103.

图/表 12

图1

图2

图3

图4

图5

图7

图6

图8

表1

图9

图10

表2

参考文献 13

[1]	张弛 . 神经网络算法在电磁泄露及脑电信息认知中的应用[D]. 北京:北京邮电大学, 2018.
	ZHANG C . Application of neural network algorithm in electromagnetic[D]. Beijing:Beijing University of Posts and Telecommunications, 2018.
[2]	BAUER A O , . Some aspects of military line communications as deployed by the german armed forces prior to 1945[C]// In Proceedings of 5th Aunnual Colloquium,The History of Military Communications.[S.n.:s.l]. 1999: 1-21.
[3]	张南 . 计算机电磁信息泄露与视频信息认知研究[D]. 北京:北京邮电大学, 2019.
	ZHANG N . Research on computer electromagnetic information leakage and video[D]. Beijing:Beijing University of Posts and Telecommunications, 2019.
[4]	ZHU T , MA Q , ZHANG S F ,et al. Context-free attacks using keyboard acoustic emanations[C]// ACM SIGSAC Conference on Computer and Communications Security. New York:ACM Press, 2014: 453-464.
[5]	ABHISHEK S , SAXENA N . Keyboard emanations in remote voice calls:password leakage and noise(less) masking defense[C]// ACM Conference on Data and Application Security and Privacy. New York:ACM Press, 2018: 103-110.
[6]	ASONOV D , AGRAWAL R . Keyboard acoustic emanations[C]// IEEE Symposium on Security and Privacy. Piscataway:IEEE Press, 2004: 3-11.
[7]	COMPAGNO A , CONTI M , LAIN D ,et al. Don’t skype ＆ type! Acoustic eavesdropping in voice-over-IP[C]// ACM on Asia Conference on Computer and Communications Security. New York:ACM Press, 2017: 703-715.
[8]	DU H , YU Z W , XIAO D . Sensing keyboard input for computer activity recognition with a smartphone[C]// ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York:ACM Press, 2017: 25-28.
[9]	ZHENG X S , YANG S L , JIN N G ,et al. Diva:distributed voronoi-based acoustic source localization with wireless sensornetworks[C]// IEEE Conference on Computer Communications. Piscataway:IEEE Press, 2016: 1-9.
[10]	米建伟, 方晓莉, 仇原鹰 . 非平稳背景噪声下声音信号增强技术[J]. 仪器仪表学报, 2017,38(1): 17-38.
	MI J W , FANG X L , QIU Y Y . Enhancement technology for the audio signal with nonstationary background noise[J]. Chinese Journal of Scientific Instrument, 2017,38(1): 17-38.
[11]	史燕燕, 白静 . 融合CFCC和Teager能量算子倒谱参数的语音识别[J]. 计算机科学, 2019,46(5): 286-289.
	SHI Y Y , BAI J . Speech recognition combining CFCC and Teager energy operators cepstral coefficients[J]. Computer Science, 2019,46(5): 286-289.
[12]	ZHANG J , ZUO L , GAO J W . Digital instruments recognition based on PCA-BP neural network[C]// IEEE Information Technology,Networking,Electronic,and Automation Control Conference. Piscataway:IEEE Press, 2017: 928-932.
[13]	沈伟国, 王巍 . 基于顽健线性判别分析的击键特征识别方法[J]. 通信学报, 2017,38(Z2): 26-29.
	SHEN W G , WANG W . Keystroke features recognition based on stable linear discriminant analysis[J]. Journal on Communications, 2017,38(Z2): 26-29.

方法	输入数据形式	准确率	相关系数
SVM	CFCC	43.46%	0.25
BP	CFCC	90%	0.85
BP	CSG	96.15%	0.919 6

方法	安静环境	嘈杂环境
CFCC+BP	91%	83%
CSG+BP	96%	90%

[1]	陈晋音, 熊海洋, 马浩男, 郑雅羽. 基于对比学习的图神经网络后门攻击防御方法[J]. 通信学报, 2023, 44(4): 154-166.
[2]	李建锋, 刘哲宇, 荣洋, 李展, 廖柏林, 屈林曦, 刘志杰, 林琨煌. 用于线性噪声时变凸二次规划的归零神经网络[J]. 通信学报, 2023, 44(4): 226-233.
[3]	林云, 徐怀韬, 王森, 张思成, 庄龙. 基于特征融合的通信语音干扰效果客观评估[J]. 通信学报, 2023, 44(3): 105-116.
[4]	杨宏宇, 杨海云, 张良, 成翔. 基于特征依赖图的源代码漏洞检测方法[J]. 通信学报, 2023, 44(1): 103-117.
[5]	何世文, 袁军, 安振宇, 张敏, 黄永明, 张尧学. 基于图神经网络的联合用户调度与波束成形优化算法[J]. 通信学报, 2022, 43(7): 73-84.
[6]	冷涛, 蔡利君, 于爱民, 朱子元, 马建刚, 李超飞, 牛瑞丞, 孟丹. 基于系统溯源图的威胁发现与取证分析综述[J]. 通信学报, 2022, 43(7): 172-188.
[7]	李昂, 陈建新, 魏昕, 周亮. 面向6G的跨模态信号重建技术[J]. 通信学报, 2022, 43(6): 28-40.
[8]	王晓丹, 李京泰, 宋亚飞. DDAC：面向卷积神经网络图像隐写分析模型的特征提取方法[J]. 通信学报, 2022, 43(5): 68-81.
[9]	廖育荣, 王海宁, 林存宝, 李阳, 方宇强, 倪淑燕. 基于深度学习的光学遥感图像目标检测研究进展[J]. 通信学报, 2022, 43(5): 190-203.
[10]	张帆, 黄赟, 方子茁, 郭威. 卷积神经网络的损失最小训练后参数量化方法[J]. 通信学报, 2022, 43(4): 114-122.
[11]	朱政宇, 侯庚旺, 黄崇文, 孙钢灿, 郝万明, 梁静. 基于并行CNN的RIS辅助D2D保密通信系统资源分配算法[J]. 通信学报, 2022, 43(3): 172-179.
[12]	霍俊彦, 王丹妮, 马彦卓, 万帅, 杨付正. 基于轻量级全连接网络的H.266/VVC分量间预测[J]. 通信学报, 2022, 43(2): 143-155.
[13]	龙华, 黄张衡, 邵玉斌, 杜庆治, 苏树盟. 基于改进CFCC特征提取的语种识别算法研究[J]. 通信学报, 2022, 43(12): 211-221.
[14]	朱政宇, 陈鹏飞, 王梓晅, 巩克现, 吴迪, 王忠勇. 基于Swin-Transformer的短波协议信号识别[J]. 通信学报, 2022, 43(11): 127-135.
[15]	熊金波, 周永洁, 毕仁万, 万良, 田有亮. 边缘协同的轻量级隐私保护分类框架[J]. 通信学报, 2022, 43(1): 127-137.

基于声音空间梯度的高稳健性击键识别方法

High-roubustness keystroke recognition method based on acoustic spatial gradient

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 13

相关文章 15

Metrics

推荐阅读 0