计算机科学 ›› 2024, Vol. 51 ›› Issue (9): 371-382.doi: 10.11896/jsjkx.230800076
卢徐霖, 李志华
LU Xulin, LI Zhihua
摘要： 现有物联网设备识别方法存在表征设备指纹的特征维度单一、流量特征信息选择不完备的问题,导致对流量特征的表征能力不足,且未充分挖掘多个网络模型的识别潜能,进而导致识别效果不够理想。针对上述不足,文中提出了一种融合多模态物联网设备指纹与集成学习的物联网设备识别(MultiDI)方法。首先,为了在保证流量特征信息不丢失的同时,提高物联网设备指纹的特征表示能力,通过将改进的Nilsimsa算法和数据图像化处理方法相结合,研究并提出一种多模态物联网设备指纹生成算法;然后,基于所生成的物联网设备指纹特征,使用3个神经网络模型深入挖掘多模态指纹特征的不同维度信息,对物联网设备的流量特征进行更充分的学习和识别;最后,为了进一步挖掘多个网络模型的识别潜能,通过分类加权和LeakyRelu激活函数构建分类连接网络,借助所提出的分类连接网络进行集成学习,用以整合多个网络模型的识别结果从而增强MultiDI方法的物联网设备识别准确率。实验结果表明,MultiDI方法在3个数据集上分别取得了91.3%,98.6%和99.2%的加权F1值,验证了该方法的有效性;与多种物联网设备识别方法相比,在识别效果上呈现出相对优势,验证了该方法的高效性。
中图分类号:
| [1]STATISTA RESEARCH DEPARTMENT.Internet of Things(IoT) connected devices installed base worldwide from 2015 to 2025[EB/OL].https://www.statista.com/statistics/471264/iot-number-of-connected-devices-worldwide/. [2]FAN L N,LI C C,WU Y C,et al.Survey on IoT Device Identification and Anomaly Detection [J].Ruan Jian Xue Bao,2024,35(1):288-308. [3]JMILA H,BLANC G,SHAHID M,et al.A Survey of Smart Home IoT Device Classification Using Machine Learning-Based Network Traffic Analysis[J].IEEE Access,2022(10):97117-97141. [4]ANTONAKAKIS M,APRIL T,BAILEY M,et al.Understan-ding the Mirai Botnet[C]//26th USENIX Security Symposium.2017:1093-1110. [5]WANODE S,ANAND M,MITRA B.Optimal Feature Set Selection for IoT Device Fingerprinting on Edge Infrastructure using Machine Intelligence[C]//IEEE INFOCOM 2022-IEEE Conference on Computer Communications Workshops(INFOCOM WKSHPS).2022:1-6. [6]RADHAKRISHNAN S,ULUAGAC A S,ULUAGAC R.GTID:A Technique for Physical Device and Device Type Fingerprinting[J].IEEE Transactions on Dependable and Secure Computing,2015,12(5):519-532. [7]YUAN H L,HU A Q.Preamble-based detection of Wi-Fi transmitter RF fingerprints[J].Electronics Letters,2010(46):1165-1167. [8]FENG X,LI Q,HAN Q,et al.Active Profiling of Physical Devices at Internet Scale[C]//2016 25th International Conference on Computer Communication and Networks(ICCCN).2016:1-9. [9]MIETTINEN M,MARCHAL S,HAFEEZ I,et al.IoT sentinel: Automated device-type identification for security enforcement in iot[C]//2017 IEEE 37th International Conference on Distributed Computing Systems(ICDCS).IEEE,2017:2177-2184. [10]BRUHADESHWAR B,MAALVIKA B,JORDANP,et al.Behavioral Fingerprinting of IoT Devices[C]//Association for Computing Machinery.2018:41-50. [11]KOSTAS K,JUST M,LONES M A.IoTDevID:A Behavior-Based Device Identification Method for the IoT[J].IEEE Internet of Things Journal,2022,9(23):23741-23749. [12]KOTAK J,ELOVICI Y.IoT Device Identification Using Deep Learning[C]//13th International Conference on Computational Intelligence in Security for Information Systems.2020:76-86. [13]YIN F,YANG L,WANG Y,et al.IoT ETEI:End-to-End IoTDevice Identification Method[C]//2021 IEEE Conference on Dependable and Secure Computing(DSC).2021:1-8. [14]THOM J,THOM N,SENGUPTA S,et al.Smart Recon:Net-work Traffic Fingerprinting for IoT Device Identification[C]//2022 IEEE 12th Annual Computing and Communication Workshop and Conference(CCWC).2022:72-79. [15]HAO Q X,RONG Z,XIE L J,et al.Online IoT Device Identification Method Based on Bi-LSTM[J].Journal of Xi'an University of Science and Technology,2023,43(2):422-430. [16]PANG Y L,LI X W.Feature Selection Algorithm of Network Traffic Based on SU and AMB[J].Computer Systems & Applications,2022,31(4):281-287. [17]JACOBS R.Tshark[EB/OL].https://tshark.dev/export/. [18]GUILLAUME G, PIERRE V,et al.Scapy[EB/OL].https://scapy.net/. [19]ERNESTO D,SABRINA V,STEFANO P,et al.An Open Digest-based Technique for Spam Detection.Parallel and Distributed Computing Systems[J/OL].https://www.researchgate.net/publication/220922423_An_Open_Digest-based_Technique_for_Spam_Detection. [20]FUENTEALBA P,CHAMORRO E,SANTOS J C.Chapter 5Understanding and using the electron localization function[J].Theoretical Aspects of Chemical Reactivity,2008(19):57-85. [21]JU C,BIBAUT A,LAAN M.The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification[J].Journal of Applied Statistics,2018,45(15):2800-2818. [22]HUANG G,LIU Z,MAATEN L V D,et al.Densely Connected Convolutional Networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.2018. [23]FRANÇOIS C.Xception:Deep Learning with Depthwise Separable Convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition.2017. [24]MIETTINEN M,MARCHAL S,HAFEEZ I,et al.IoT Sentinel:Automated Device-Type Identification for Security Enforcement in IoT[C]//2017 IEEE 37th International Conference on Distributed Computing Systems.2017:2511-2514. [25]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,2019,18(8):1745-1759. [26]CHARYYEV B,GUNES M H.IoT Traffic Flow Identification using Locality Sensitive Hashes[C]//2020 IEEE International Conference on Communications(ICC 2020).2020:1-6. |
|
||
首页