Emergent Deep Learning for Anomaly Detection in Internet of Everything

This research presents a new generic deep learning (DL) framework for anomaly detection in the Internet of Everything (IoE). It combines decomposition methods, deep neural networks, and evolutionary computation to better detect outliers in IoE environments. The data set is first decomposed into clusters, while similar observations in the same cluster are grouped. Five clustering algorithms were used for this purpose. The generated clusters are then trained using DL architectures. In this context, we propose a new recurrent neural network for training time-series data. Two evolutionary computational algorithms are also proposed: 1) the genetic and 2) the bee swarm, to fine-tune the training step. These algorithms consider the hyperparameters of the trained models and try to find the optimal values. The proposed solutions have been experimentally evaluated for two use cases: 1) road traffic outlier detection and 2) network intrusion detection. The results show the advantages of the proposed solutions and a clear superiority compared to state-of-the-art approaches.

[1]  Meng Jiang,et al.  A Survey on Data-driven Network Intrusion Detection , 2021, ACM Comput. Surv..

[2]  Mohammad Reza Nosouhi,et al.  Bushfire Risk Detection Using Internet of Things: An Application Scenario , 2021, IEEE Internet of Things Journal.

[3]  Mohammad Nuruzzaman Bhuiyan,et al.  Internet of Things (IoT): A Review of Its Enabling Technologies in Healthcare Applications, Standards Protocols, Security, and Market Opportunities , 2021, IEEE Internet of Things Journal.

[4]  Weishan Zhang,et al.  Blockchain-Based Federated Learning for Device Failure Detection in Industrial IoT , 2021, IEEE Internet of Things Journal.

[5]  Gautam Srivastava,et al.  Privacy-Preserving Multiobjective Sanitization Model in 6G IoT Environments , 2021, IEEE Internet of Things Journal.

[6]  Bing Ouyang,et al.  Initial Development of the Hybrid Aerial Underwater Robotic System (HAUCS): Internet of Things (IoT) for Aquaculture Farms , 2021, IEEE Internet of Things Journal.

[7]  Samia Bouzefrane,et al.  A modified LOF-based approach for outlier characterization in IoT , 2020, Annals of Telecommunications.

[8]  Ali Kashif Bashir,et al.  Towards sFlow and adaptive polling sampling for deep learning based DDoS detection in SDN , 2020, Future Gener. Comput. Syst..

[9]  Milena Lazarova,et al.  A Hybrid PSO-MiLOF Approach for Outlier Detection in Streaming Data , 2020, 2020 43rd International Conference on Telecommunications and Signal Processing (TSP).

[10]  Djamel Djenouri,et al.  DFIOT: Data Fusion for Internet of Things , 2020, Journal of Network and Systems Management.

[11]  Ying Zhong,et al.  HELAD: A novel network anomaly detection model based on heterogeneous ensemble learning , 2020, Comput. Networks.

[12]  D. Siracusa,et al.  Lucid: A Practical, Lightweight Deep Learning Solution for DDoS Attack Detection , 2020, IEEE Transactions on Network and Service Management.

[13]  Mohamed Amine Ferrag,et al.  Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study , 2020, J. Inf. Secur. Appl..

[14]  Jerry Chun-Wei Lin,et al.  Exploring Pattern Mining Algorithms for Hashtag Retrieval Problem , 2020, IEEE Access.

[15]  M. S. Desouki,et al.  Big data analysis and distributed deep learning for next-generation intrusion detection system optimization , 2019, Journal of Big Data.

[16]  John W. Polak,et al.  Traffic Monitoring and Anomaly Detection based on Simulation of Luxembourg Road Network , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[17]  Christian S. Jensen,et al.  Outlier Detection for Time Series with Recurrent Autoencoder Ensembles , 2019, IJCAI.

[18]  Albert Y. Zomaya,et al.  A Hybrid Deep Learning-Based Model for Anomaly Detection in Cloud Datacenter Networks , 2019, IEEE Transactions on Network and Service Management.

[19]  Robert H. Deng,et al.  Fair and Dynamic Data Sharing Framework in Cloud-Assisted Internet of Everything , 2019, IEEE Internet of Things Journal.

[20]  Georgios Kambourakis,et al.  Introducing Deep Learning Self-Adaptive Misuse Network Intrusion Detection Systems , 2019, IEEE Access.

[21]  Joel J. P. C. Rodrigues,et al.  Hybrid Deep-Learning-Based Anomaly Detection Scheme for Suspicious Flow Detection in SDN: A Social Multimedia Perspective , 2019, IEEE Transactions on Multimedia.

[22]  Tankut Acarman,et al.  A deep learning method to detect network intrusion through flow‐based features , 2018, Int. J. Netw. Manag..

[23]  Karishma Pawar,et al.  Deep learning approaches for video-based anomalous activity detection , 2019, World Wide Web.

[24]  Philippe Fournier-Viger,et al.  Fast and effective cluster-based information retrieval using frequent closed itemsets , 2018, Inf. Sci..

[25]  Jianxin Li,et al.  Road Traffic Speed Prediction: A Probabilistic Model Fusing Multi-Source Data , 2018, IEEE Transactions on Knowledge and Data Engineering.

[26]  D. Djenouri,et al.  Machine Learning for Smart Building Applications: Review and Taxonomy , 2018 .

[27]  Tankut Acarman,et al.  Classification of malware families based on runtime behaviors , 2017, J. Inf. Secur. Appl..

[28]  Sridhar Ramaswamy,et al.  Efficient algorithms for mining outliers from large data sets , 2000, SIGMOD '00.

[29]  George Karypis,et al.  A Comparison of Document Clustering Techniques , 2000 .

[30]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[31]  H. Edelsbrunner,et al.  Efficient algorithms for agglomerative hierarchical clustering methods , 1984 .

[32]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .