Deep Learning with Dense Random Neural Networks for Detecting Attacks Against IoT-Connected Home Environments

In this paper, we analyze the network attacks that can be launched against IoT gateways, identify the relevant metrics to detect them, and explain how they can be computed from packet captures. We also present the principles and design of a deep learning-based approach using dense random neural networks (RNN) for the online detection of network attacks. Empirical validation results on packet captures in which attacks were inserted show that the Dense RNN correctly detects attacks.

[1]  Erol Gelenbe,et al.  Energy Life-Time of Wireless Nodes with Network Attacks and Mitigation , 2018, 2018 IEEE International Conference on Communications Workshops (ICC Workshops).

[2]  Erol Gelenbe,et al.  Deep Learning with Dense Random Neural Networks , 2017, ICMMI.

[3]  Erol Gelenbe,et al.  Single-cell based random neural network for deep learning , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[4]  Erol Gelenbe,et al.  Deep Learning in Multi-Layer Architectures of Dense Nuclei , 2016, ArXiv.

[5]  Mahmut T. Kandemir,et al.  The Sleep Deprivation Attack in Sensor Networks: Analysis and Methods of Defense , 2006, Int. J. Distributed Sens. Networks.

[6]  Frank Stajano,et al.  The Resurrecting Duckling: Security Issues for Ad-hoc Wireless Networks , 1999, Security Protocols Workshop.

[7]  Erol Gelenbe,et al.  Deep learning with random neural networks , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[8]  Ashwani Kumar,et al.  A Survey in Energy Drain Attacks and Their Countermeasures in Wireless Sensor Networks , 2014 .

[9]  Karl N. Levitt,et al.  A Synchronization Attack and Defense in Energy-Efficient Listen-Sleep Slotted MAC Protocols , 2008, 2008 Second International Conference on Emerging Security Information, Systems and Technologies.

[10]  Erol Gelenbe,et al.  Random Neural Networks with Negative and Positive Signals and Product Form Solution , 1989, Neural Computation.

[11]  Scott D Dalrymple.  Comparison of ZigBee Replay Attacks Using a Universal Software Radio Peripheral and USB Radio , 2014 .

[12]  Hans-Joachim Hof,et al.  Fighting Insomnia: A Secure Wake-Up Scheme for Wireless Sensor Networks , 2009, 2009 Third International Conference on Emerging Security Information, Systems and Technologies.

[13]  M. Brownfield,et al.  Wireless sensor network denial of sleep attack , 2005, Proceedings from the Sixth Annual IEEE SMC Information Assurance Workshop.

[14]  Erol Gelenbe,et al.  Learning in the Recurrent Random Neural Network , 1992, Neural Computation.

[15]  Erol Gelenbe,et al.  Impact of Signaling Storms on Energy Consumption and Latency of LTE User Equipment , 2015, 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems.

[16]  Yee Wei Law,et al.  Energy-efficient link-layer jamming attacks against wireless sensor network MAC protocols , 2005, TOSN.

[17]  Sebastian Mödersheim,et al.  Detecting and Preventing Beacon Replay Attacks in Receiver-Initiated MAC Protocols for Energy Efficient WSNs , 2013, NordSec.

[18]  M.Kanchana,et al.  VAMPIRE ATTACKS: DRAINING LIFE FROM WIRELESS AD HOC SENSOR NETWORKS , 2014 .

[19]  Erol Gelenbe,et al.  Non-negative Autoencoder with Simplified Random Neural Network , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).