A LSTM-Based Channel Fingerprinting Method for Intrusion Detection

Intrusion detection is a crucial issue for 5th generation (5G) access networks to securely support various services. Traditional cryptographic key-based solutions are not suitable for severe resources-constrained networks, such as the Internet of Things (IoT). In this paper, we propose a lightweight intrusion detection mechanism by exploring physical layer attributes that are unique and difficult to impersonate. Specifically, a long-short memory network (LSTM) is employed as an intelligent classifier to distinguish different transmitters based on channel state information (CSI) features. Then we develop a comprehensive 5G NR channel detection model based on LSTM under dynamic channel conditions to identify malicious attacks by intelligently analyzing CSI. The simulation results demonstrate that the proposed solution improves detection accuracy and successfully prevent systems from spoofing attacks.

[1]  Waqas Aman,et al.  Channel Impulse Response-based Physical Layer Authentication in a Diffusion-based Molecular Communication System , 2019, 2019 UK/ China Emerging Technologies (UCET).

[2]  3rd Generation Partnership Project; Technical Specification Group Radio Access Network; Utran Iu Interface Layer 1 (release 1999) , 2022 .

[3]  Walid Saad,et al.  Machine Learning for Wireless Networks with Artificial Intelligence: A Tutorial on Neural Networks , 2017, ArXiv.

[4]  Lajos Hanzo,et al.  Learning-Aided Physical Layer Authentication as an Intelligent Process , 2018, IEEE Transactions on Communications.

[5]  Xiaoying Qiu,et al.  A Learning Approach for Physical Layer Authentication Using Adaptive Neural Network , 2020, IEEE Access.

[6]  Ming Liu,et al.  Deep Learning Based RF Fingerprint Identification Using Differential Constellation Trace Figure , 2020, IEEE Transactions on Vehicular Technology.

[7]  Xinyin Xiang,et al.  Anti-Quantum Fast Authentication and Data Transmission Scheme for Massive Devices in 5G NB-IoT System , 2019, IEEE Internet of Things Journal.

[8]  Hui Li,et al.  A Survey on Security Aspects for 3GPP 5G Networks , 2020, IEEE Communications Surveys & Tutorials.

[9]  Tarik Taleb,et al.  Physical Layer Authentication for Massive MIMO Systems With Hardware Impairments , 2020, IEEE Transactions on Wireless Communications.

[10]  Maode Ma,et al.  Fast and efficient physical layer authentication for 5G HetNet handover , 2017, 2017 27th International Telecommunication Networks and Applications Conference (ITNAC).

[11]  Dongmei Zhao,et al.  Physical Layer Authentication Based on CFO and Visibility Graph , 2018, 2018 International Conference on Networking and Network Applications (NaNA).

[12]  Stefan Parkvall,et al.  NR - The New 5G Radio-Access Technology , 2017, 2018 IEEE 87th Vehicular Technology Conference (VTC Spring).

[13]  Xianbin Wang,et al.  Integrating PHY Security Into NDN-IoT Networks By Exploiting MEC: Authentication Efficiency, Robustness, and Accuracy Enhancement , 2019, IEEE Transactions on Signal and Information Processing over Networks.

[14]  Kui Ren,et al.  Wireless Physical-Layer Identification: Modeling and Validation , 2015, IEEE Transactions on Information Forensics and Security.

[15]  Stratis Ioannidis,et al.  No Radio Left Behind: Radio Fingerprinting Through Deep Learning of Physical-Layer Hardware Impairments , 2020, IEEE Transactions on Cognitive Communications and Networking.

[16]  Qian Wang,et al.  Deep Neural Networks for CSI-Based Authentication , 2019, IEEE Access.

[17]  Xianbin Wang,et al.  Physical Layer Authentication Enhancement Using Two-Dimensional Channel Quantization , 2016, IEEE Transactions on Wireless Communications.