SAIFE: Unsupervised Wireless Spectrum Anomaly Detection with Interpretable Features

Detecting anomalous behavior in wireless spectrum is a demanding task due to the sheer complexity of the electromagnetic spectrum use. Wireless spectrum anomalies can take a wide range of forms from the presence of an unwanted signal in a licensed band to the absence of an expected signal, which makes manual labeling of anomalies difficult and suboptimal. We present, Spectrum Anomaly Detector with Interpretable FEatures (SAIFE), an Adversarial Autoencoder (AAE) based anomaly detector for wireless spectrum anomaly detection using Power Spectral Density (PSD) data which achieves good anomaly detection and localization in an unsupervised setting. In addition, we investigate the model’s capabilities to learn interpretable features such as signal bandwidth, class and center frequency in a semi-supervised fashion. Along with anomaly detection the model exhibits promising results for lossy PSD data compression up to 120X and semi-supervised signal classification accuracy close to 100% on three datasets just using 20% labeled samples. Finally the model is tested on data from one of the distributed Electrosense sensors over a long term of 500 hours showing its anomaly detection capabilities.

[1]  Biming Tian,et al.  Anomaly detection in wireless sensor networks: A survey , 2011, J. Netw. Comput. Appl..

[2]  Sofie Pollin,et al.  Electrosense: Open and Big Spectrum Data , 2017, IEEE Communications Magazine.

[3]  Larry J. Greenstein,et al.  ALDO: An Anomaly Detection Framework for Dynamic Spectrum Access Networks , 2009, IEEE INFOCOM 2009.

[4]  Sofie Pollin,et al.  Deep Learning Models for Wireless Signal Classification With Distributed Low-Cost Spectrum Sensors , 2017, IEEE Transactions on Cognitive Communications and Networking.

[5]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[6]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[7]  Andrew F. Cheng,et al.  A new compression algorithm for spectral and time-series data , 2003 .

[8]  Jung-Min Park,et al.  An overview of anomaly detection techniques: Existing solutions and latest technological trends , 2007, Comput. Networks.

[9]  Wang Lei,et al.  Spectrum anomalies autonomous detection in cognitive radio using Hidden Markov Models , 2015, 2015 IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC).

[10]  Miao Xie,et al.  Anomaly Detection in Wireless Sensor Networks , 2013 .

[11]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[12]  Timothy J. O'Shea,et al.  Unsupervised representation learning of structured radio communication signals , 2016, 2016 First International Workshop on Sensing, Processing and Learning for Intelligent Machines (SPLINE).

[13]  Pieter Abbeel,et al.  InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets , 2016, NIPS.

[14]  Ran El-Yaniv,et al.  Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations , 2016, J. Mach. Learn. Res..

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[17]  Xiaojiang Du,et al.  A Wideband Spectrum Data Segment Compression Algorithm in Cognitive Radio Networks , 2017, 2017 IEEE Wireless Communications and Networking Conference (WCNC).

[18]  Jeffrey H. Reed,et al.  Deep Predictive Coding Neural Network for RF Anomaly Detection in Wireless Networks , 2018, 2018 IEEE International Conference on Communications Workshops (ICC Workshops).

[19]  Chao Li,et al.  Anomaly detection of spectrum in wireless communication via deep auto-encoders , 2017, The Journal of Supercomputing.

[20]  Timothy J. O'Shea,et al.  Recurrent Neural Radio Anomaly Detection , 2016, ArXiv.