网络出版日期: 2025-01-25
基金资助
河南省重点研发专项(221111321200)
版权
Hidden camera recognition method based on GoP features
Online published: 2025-01-25
Supported by
Key Research and Development Project of Henan Province (221111321200)
Copyright
结构特性是推断设备类别和型号的重要依据之一,然而由于Wi-Fi网络通过WPA/WPA2、WPA-PSK/WPA2-PSK、WEP等多种方式加密,现有基于无线流量特征的隐藏摄像头识别方法难以从加密后的数据中提取结构特性。为此,提出了一种基于GoP(Group of Pictures)特征的隐藏摄像头识别方法CEASE。所提方法首先采用对比时间间隔策略恢复丢失数据包,然后基于摄像头视频编码和传输原理构建GoP,并在GoP上使用聚合函数提取特征向量,最后基于已有LightGBM方法进行训练并对设备类别和型号进行推断。在大量实测流量上开展了相关实验并与近年来的典型识别方法进行了对比,结果表明:与使用手工构造特征的DeWiCam和ScamF方法相比,CEASE方法设备类别识别准确率分别提升了4.2%和3.4%、摄像头型号识别准确率分别提升了32.9%和38.4%;与同样在多窗口上提取聚合特征的Lumos方法相比,CEASE方法设备类别识别准确率提升了1.6%、摄像头型号识别准确率提升了8.3%。
马永强 , 魏果 , 刘文艳 , 刘粉林 . 基于GoP特征的隐藏摄像头识别方法[J]. 网络空间安全科学学报, 2024 , 2(5) : 109 -120 . DOI: 10.20172/j.issn.2097-3136.240510
Structural characteristics are one of the important bases for inferring device categories and models. However, because Wi-Fi networks are encrypted in various ways such as WPA/WPA2, WPA-PSK/WPA2-PSK, WEP, etc., existing hidden camera identification methods based on wireless traffic characteristics are difficult to extract structural characteristics from encrypted data. To solve this problem, a hidden camera identification method CEASE based on the GoP(Group of Pictures)features was proposed. The proposed method first employed a nearest neighbor time interval contrast strategy to recover lost packets. Then, it constructed GoPs based on the principles of camera video encoding and transmission, extracting feature vectors using aggregation functions on these GoPs. Finally, the LightGBM method was applied for training and to infer device categories and models. Extensive experiments were conducted on substantial real-world traffic data, with comparisons made against representative methods in recent years. The results demonstrated that compared to DeWiCam and ScamF, which used manually crafted features, the proposed method improved device category recognition accuracy by 4.2% and 3.4% respectively, and camera model recognition accuracy by 32.9% and 38.4% respectively. When compared to Lumos, another method that extracted aggregated features across multiple windows, the device category recognition accuracy was improved by 1.6%, and the camera model recognition accuracy was enhanced by 8.3%.
Key words: camera recognition; GoP features; video encoding; aggregation functions; LightGBM
表 1 部分产品和应用的最大分组长度Table 1 Maximum packet length for some products and applications |
| 序号 | 名称 | 设备型号/应用 | 制造商 | 最大分组长度 |
| 1 | 摄像头 | CS-C6CN | 萤石 | 1 450 |
| 2 | 摄像头 | CS-C6 | 萤石 | 1 512 |
| 3 | 摄像头 | LC-TA3-4M | 乐橙 | 1 126 |
| 4 | 摄像头 | CMSXJ16A | 小米 | 1 154 |
| 5 | 摄像头 | AC1P | 360 | 1 102 |
| 6 | 摄像头 | AK-WH8310PR | 华为 | 1 494 |
| 7 | 短视频 | 抖音 | 字节跳动 | 3 197 |
| 8 | 网络直播 | 快手视频 | 快手 | 1 450 |
| 9 | 电视剧 | 腾讯视频 | 腾讯 | 3 825 |
| 10 | 上传视频 | 微信 | 腾讯 | 1 470 |
表 2 各分类器性能对比Table 2 Performance comparison of various classifiers |
| 序号 | 分类器 | 平均准确率 | 训练执行时间/s | 内存消耗/GB |
| 1 | Extra Trees | 83.12 % | 58 | 9.5 |
| 2 | Random Forest | 82.53 % | 65 | 8.6 |
| 3 | XGBoost | 95.23 % | 901 | 6.7 |
| 4 | LightGBM | 94.51% | 132 | 1.9 |
| 1 |
SIVARAMAN V, GHARAKHEILI H H, FERNANDES C, et al. Smart IoT devices in the home: security and privacy implications[J]. IEEE Technology and Society Magazine, 2018, 37 (2): 71- 79.
|
| 2 |
SONG S, LI V O K, LAM J C K, et al. Personalized ambient pollution estimation based on stationary-camera-taken images under cross-camera information sharing in smart city[J]. IEEE Internet of Things Journal, 2023, 10 (17): 15420- 15430.
|
| 3 |
JAKKAMSETTI S,KIM Y,TSUDIK G. Caveat (IoT) emptor:towards transparency of IoT device presence[C]//Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security. New York:ACM Press,2023:1347-1361.
|
| 4 |
CHENG Y S, JI X Y, LU T Y, et al. On detecting hidden wireless cameras: a traffic pattern-based approach[J]. IEEE Transactions on Mobile Computing, 2019, 19 (4): 907- 921.
|
| 5 |
LIU Z W,LIN F,WANG C,et al. CamRadar:hidden camera destection leveraging amplitude-modulated sensor images embedded in electromagnetic emanations[C]//Proceedings of the 2023 ACM on Interactive,Mobile,Wearable and Ubiquitous Technologies. New York:ACM Press,2023:1-25.
|
| 6 |
HE Y,HE Q,FANG S,et al. MotionCompass:pinpointing wireless camera via motion-activated traffic [C]//Proceedings of the 19th Annual International Conference on Mobile Systems,Applications,and Services. New York:ACM Press,2021:215-227.
|
| 7 |
SAMI S,TAN S R X,SUN B,et al. LAPD:hidden spy camera detection using smartphone time-of-flight sensors[C]//Proceedings of the 19th ACM Conference on Embedded Networked Sensor Systems. New York:ACM Press,2021:288-301.
|
| 8 |
LEE J,SEO S,YANG T,et al. AI-aided hidden camera detection and localization based on raw IoT network traffic[C]// Proceedings of the 47th IEEE Conference on Local Computer Networks. Piscataway:IEEE Press,2022:315-318.
|
| 9 |
MIETTINEN M,MARCHAL S,HAFEEZ I,et al. IoT sentinel Demo:automated device-type identification for security enforcement in IoT[C]// Proceedings of 2017 IEEE 37th International Conference on Distributed Computing Systems. Piscataway:IEEE Press,2017:2177-2184.
|
| 10 |
SIVANATHAN A, GHARAKHEILI H H, LOI F, et al. Classifying IoT devices in smart environments using network traffic characteristics[J]. IEEE Transactions on Mobile Computing, 2018, 18 (8): 1745- 1759.
|
| 11 |
芮志清. 网络摄像头安全威胁检测系统的设计与实现[D]. 北京:中国科学院大学,2020.
RUI Z Q. Design and implementation of web camera security threat detection system[D]. Beijing:University of Chinese Academy of Sciences,2020.
|
| 12 |
ZHANG Y F,LIN Y,DOU Z,et al. Monitoring and identification of Wi-Fi devices for internet of things security[C]//Proceedings of the IEEE Globecom Workshops. Piscataway:IEEE Press,2019:1-5.
|
| 13 |
FENG X,LI Q,WANG H N,et al. Acquisitional rule-based engine for discovering internet-of-things devices[C]//Proceedings of the 27th USENIX Security Symposium. Berkeley:USENIX Association,2018:327-341.
|
| 14 |
SALMAN O, ELHAJJ I H, CHEHAB A, et al. A machine learning based framework for IoT device identification and abnormal traffic detection[J]. Transactions on Emerging Telecommunications Technologies, 2022, 33 (3): e3743.
|
| 15 |
ORTIZ J,CRAWFORD C H,LE F. DeviceMien:network device behavior modeling for identifying unknown IoT devices[C]//Proceedings of the International Conference on Internet of Things Design and Implementation. New York:ACM Press,2019:106-117.
|
| 16 |
SINGH A D,GARCIA L,NOOR J,et al. I always feel like somebody's sensing me! a framework to detect,identify,and localize clandestine wireless sensors[C]//Proceedings of the 30th USENIX Security Symposium. Berkeley:USENIX Association,2021:1829-1846.
|
| 17 |
HEO J,GIL S,JUNG Y,et al. Are there wireless hidden cameras spying on me?[C]//Proceedings of the Annual Computer Security Applications Conference. New York:ACM Press,2022:714-726.
|
| 18 |
WAMPLER C,ULUAGAC S,BEYAH R. Information leakage in encrypted IP video traffic[C]// Proceedings of the 2015 IEEE global Communications Conference( GLOBECOM 2015). Piscataway:IEEE Press,2015:1-7.
|
| 19 |
LIU T,LIU Z Y,HUANG J,et al. Detecting wireless spy cameras via stimulating and probing[C]// Proceedings of the 16th Annual International Conference on Mobile Systems,Applications,and Services. New York:ACM Press,2018:243-255.
|
| 20 |
KUMAR R, SWARNKAR M, SINGAL G, et al. IoT network traffic classification using machine learning algorithms: an experimental analysis[J]. IEEE Internet of Things Journal, 2021, 9 (2): 989- 1008.
|
| 21 |
JAGANNATH J, POLOSKY N, JAGANNATH A, et al. Machine learning for wireless communications in the internet of things: a comprehensive survey[J]. Ad Hoc Networks, 2019, 93, 101913- 102010.
|
| 22 |
CHENG Y,JI X,LU T,et al. DeWiCam:detecting hidden wireless cameras via smartphones[C]// Proceedings of the 2018 Asia Conference on Computer and Communications Security. New York:ACM Press,2018:1-13.
|
| 23 |
SHARMA R A,SOLTANAGHAEI E,ROWE A,et al. Lumos:identifying and localizing diverse hidden IoT devices in an unfamiliar environment[C]//Proceedings of the 31st USENIX Security Symposium. Berkeley:USENIX Association,2022:1095-1112.
|
| 24 |
YU Z Y,LI Z H,CHANG Y,et al. HeatDeCam:detecting hidden spy cameras via thermal emissions[C]// Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. New York:ACM Press,2022:3107-3120.
|
| 25 |
WIEGAND T, SULLIVAN G J, BJONTEGAARD G, et al. Overview of the H. 264/AVC video coding standard[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2003, 13 (7): 560- 576.
|
| 26 |
PASTUSZAK G, ABRAMOWSKI A. Algorithm and architecture design of the H. 265/HEVC intra encoder[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2015, 26 (1): 210- 222.
|
| 27 |
JIANG M Q,YI X Q,LING N. Improved frame-layer rate control for H. 264 using MAD ratio[C]// Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS 2004). Piscataway:IEEE Press,2004:813-816.
|
| 28 |
DEFRANCESCO R, SCHRENK H. Intelligent non-volatile memory for smart cards[J]. IEEE Transactions on Consumer Electronics, 1986, (3): 604- 607.
|
| 29 |
CAO Y, MIAO Q G, LIU J C, et al. Advance and prospects of AdaBoost algorithm[J]. Acta Automatica Sinica, 2013, 39 (6): 745- 758.
|
| 30 |
NATEKIN A, KNOLL A C. Gradient boosting machines, a tutorial[J]. Frontiers in Neurorobotics, 2013, 7, 21.
|
| 31 |
HANCOCK J T, KHOSHGOFTAAR T M. CatBoost for big data: an interdisciplinary review[J]. Journal of Big Data, 2020, 7 (1): 1- 45.
|
| 32 |
MEIDAN Y, BOHADANA M, MATHOV Y, et al. N-BaIoT: network-based detection of IoT botnet attacks using deep autoencoders[J]. IEEE Pervasive Computing, 2018, 17 (3): 12- 22.
|
| 33 |
CHEN T, HE T, Benesty M C. XGBoost: extreme gradient boosting[J]. R Package Version 0. 4-2, 2015, 1 (4): 1- 4.
|
/
| 〈 |
|
〉 |