Class-Incremental Learning for Wireless Device Identification in IoT

This document provides a formal proof and supple- mentary information of the paper: Class-Incremental Learning for Wireless Device Identification in IoT. The original paper focuses on providing a novel and efficient incremental learning algorithm. In this document, we explicitly explain why the mem- ory representations (latent device fingerprints in our application) in Artificial Neural Networks approximate orthogonality with insights for the invention of our Channel Separation Incremental Learning algorithm.

[1]  Srinivas Devadas,et al.  Physical Unclonable Functions and Applications: A Tutorial , 2014, Proceedings of the IEEE.

[2]  Christian Brecher,et al.  Cyber-Physical Systems: Foundations, Principles and Applications , 2016 .

[3]  Rashid Rashidzadeh,et al.  Wireless device identification using oscillator control voltage as RF fingerprint , 2017, 2017 IEEE 30th Canadian Conference on Electrical and Computer Engineering (CCECE).

[4]  Bernt Schiele,et al.  Mnemonics Training: Multi-Class Incremental Learning Without Forgetting , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Jianqiang Li,et al.  Machine Learning for the Detection and Identification of Internet of Things Devices: A Survey , 2021, IEEE Internet of Things Journal.

[6]  Houbing Song,et al.  Deep Learning Enabled Reliable Identity Verification and Spoofing Detection , 2020, WASA.

[7]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[8]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[9]  Jean-Marie Gorce,et al.  Transmitter Classification With Supervised Deep Learning , 2019, CrownCom.

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

[11]  Jianqiang Li,et al.  Zero-Bias Deep Learning for Accurate Identification of Internet-of-Things (IoT) Devices , 2020, IEEE Internet of Things Journal.

[12]  Sung Ju Hwang,et al.  Lifelong Learning with Dynamically Expandable Networks , 2017, ICLR.

[13]  Tomaso A. Poggio,et al.  Regularization Theory and Neural Networks Architectures , 1995, Neural Computation.

[14]  Debayan Das,et al.  RF-PUF: Enhancing IoT Security Through Authentication of Wireless Nodes Using In-Situ Machine Learning , 2018, IEEE Internet of Things Journal.

[15]  Sabina Jeschke,et al.  Smart Cities: Foundations, Principles, and Applications , 2017 .

[16]  Juquan Mao,et al.  Intelligent Reflecting Surface Assisted Mobile Edge Computing for Internet of Things , 2021, IEEE Wireless Communications Letters.

[17]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[18]  Bogdan Raducanu,et al.  Generative Feature Replay For Class-Incremental Learning , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[19]  Christoph H. Lampert,et al.  Towards Understanding Knowledge Distillation , 2019, ICML.

[20]  Jianhang Huang,et al.  Communication transmitter individual feature extraction method based on stacked denoising autoencoders under small sample prerequisite , 2017, 2017 7th IEEE International Conference on Electronics Information and Emergency Communication (ICEIEC).

[21]  Houbing Song,et al.  Security of the Internet of Things: Vulnerabilities, Attacks, and Countermeasures , 2019, IEEE Communications Surveys & Tutorials.

[22]  Stratis Ioannidis,et al.  Deep Learning Convolutional Neural Networks for Radio Identification , 2018, IEEE Communications Magazine.

[23]  Rahim Tafazolli,et al.  Fed-IIoT: A Robust Federated Malware Detection Architecture in Industrial IoT , 2020, IEEE Transactions on Industrial Informatics.

[24]  Sabina Jeschke,et al.  Industrial Internet of Things: Cybermanufacturing Systems , 2016 .

[25]  Wenyuan Xu,et al.  FBSleuth: Fake Base Station Forensics via Radio Frequency Fingerprinting , 2018, AsiaCCS.

[26]  H. Song,et al.  A Decade Survey of Transfer Learning (2010–2020) , 2020, IEEE Transactions on Artificial Intelligence.

[27]  Andreas S. Tolias,et al.  Generative replay with feedback connections as a general strategy for continual learning , 2018, ArXiv.

[28]  Alexandra Libby,et al.  Rotational Dynamics Reduce Interference Between Sensory and Memory Representations , 2019, Nature Neuroscience.

[29]  Houbing Song,et al.  Transfer Learning based Data-Efficient Machine Learning Enabled Classification , 2020, 2020 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech).

[30]  Yi Yu,et al.  Radio Frequency Fingerprint Identification Based on Denoising Autoencoders , 2019, 2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob).

[31]  Ioannis Kanellos,et al.  Initial Classifier Weights Replay for Memoryless Class Incremental Learning , 2020, BMVC.

[32]  Houbing Song,et al.  Internet of Things and Big Data Analytics for Smart and Connected Communities , 2016, IEEE Access.

[33]  Glenn A. Fink,et al.  Security and Privacy in Cyber-Physical Systems , 2017 .