Hostname: page-component-78c5997874-dh8gc Total loading time: 0 Render date: 2024-11-04T01:42:54.589Z Has data issue: false hasContentIssue false
  • English
  • Français

DETECTING NETWORK-UNFRIENDLY MOBILES WITH THE RANDOM NEURAL NETWORK

Published online by Cambridge University Press:  19 May 2016

Omer H. Abdelrahman
Omer H. Abdelrahman*
Affiliation:
Intelligent Systems and Networks Group, Department of Electrical and Electronic Engineering, Imperial College London, SW7 2BT, UK E-mail: o.abd06@imperial.ac.uk
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Mobile networks are universally used for personal communications, but also increasingly used in the Internet of Things and machine-to-machine applications in order to access and control critical services. However, they are particularly vulnerable to signaling storms, triggered by malfunctioning applications, malware or malicious behavior, which can cause disruption in the access to the infrastructure. Such storms differ from conventional denial of service attacks, since they overload the control plane rather than the data plane, rendering traditional detection techniques ineffective. Thus, in this paper we describe the manner in which storms happen and their causes, and propose a detection framework that utilizes traffic measurements and key performance indicators to identify in real-time misbehaving mobile devices. The detection algorithm is based on the random neural network which is a probabilistic computational model with efficient learning algorithms. Simulation results are provided to illustrate the effectiveness of the proposed scheme.

Type
Research Article
Information
Probability in the Engineering and Informational Sciences , Volume 30 , Issue 3: Erol Gelenbe's 70th Birthday , July 2016 , pp. 514 - 531
Creative Commons
Creative Common License - CCCreative Common License - BY
This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
Copyright
Copyright © Cambridge University Press 2016

References

1.3GPP TR 23.887: Machine-type and other mobile data applications communications enhancements (release 12). http://www.3gpp.org/DynaReport/23887.htm 3GPP, December 2013, Technical Report.Google Scholar
2.Abdelbaki, H. Matlab simulator for the RNN. [Online]. Available: http://www/cs/ucf.edu/ahossam/rnnsimGoogle Scholar
3.Abdelrahman, O.H. & Gelenbe, E. (2012). Packet delay and energy consumption in non-homogeneous networks. Computer Journal 55(8): 950–964.CrossRefGoogle Scholar
4.Abdelrahman, O.H. & Gelenbe, E. (2014). Signalling storms in 3G mobile networks. In Proceedings of IEEE International Conference on Communications (ICC), Sydney, Australia, June 2014, pp. 1017–1022.CrossRefGoogle Scholar
5.Abdelrahman, O.H., Gelenbe, E., Gorbil, G., & Oklander, B. (2013). Mobile network anomaly detection and mitigation: the NEMESYS approach. In Proceedings of 28th International Symposium on Computer and Information Sciences (ISCIS), ser. LNEE. Springer, Paris, France, October 2013, vol. 264, pp. 429–438.CrossRefGoogle Scholar
6.Amrutkar, C. et al. (2013). Why is my smartphone slow? On the fly diagnosis of underperformance on the mobile internet. In Proceedings of 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN). Budapest, Hungary: IEEE Computer Society, June 2013, pp. 1–8.CrossRefGoogle Scholar
7.Arbor Networks. (2014). Worldwide infrastructure security report. 2014. [Online]. Available: http://pages.arbornetworks.com/rs/arbor/images/WISR2014.pdfGoogle Scholar
8.AT&T. (2012). Best practices for 3G and 4G app development. Whitepaper, 2012. [Online]. Available: http://developer.att.com/static-assets/documents/library/best-practices-3g-4g-app-development.pdfGoogle Scholar
9.Atalay, V. & Gelenbe, E. (1992). Parallel algorithm for colour texture generation using the random neural network model. International Journal of Pattern Recognition and Artificial Intelligence 6(02–03): 437–446.Google Scholar
10.Atalay, V., Gelenbe, E., & Yalabik, N. (1992). The random neural network model for texture generation. International Journal of Pattern Recognition and Artificial Intelligence 6(1): 131–141.Google Scholar
11.Breslau, L., Cao, P., Fan, L., Phillips, G., & Shenker, S. (1999). Web caching and Zipf-like distributions: evidence and implications. In Proceedings of IEEE INFOCOM, New York, NY, USA, vol. 1, March 1999, pp. 126–134.Google Scholar
12.Choi, Y., Yoon, C., Kim, Y., Heo, S.W., & Silvester, J. (2014). The impact of application signaling traffic on public land mobile networks. IEEE Communications Magazine 52(1): 166–172.Google Scholar
13.Coluccia, A., D'alconzo, A. & Ricciato, F. (2013). Distribution-based anomaly detection via generalized likelihood ratio test: A general maximum entropy approach. Comput. Netw. 57(17): 3446–3462.CrossRefGoogle Scholar
14.Corner, S. (2011). Angry birds + android + ads = network overload. June 2011. [Online]. Available: http://www.itwire.com/business-it-news/networking/47823Google Scholar
15.Cramer, C., Gelenbe, E., & Bakircloglu, H. (1996). Low bit-rate video compression with neural networks and temporal subsampling. Proceedings of the IEEE 84(10): 1529–1543.CrossRefGoogle Scholar
16.Cramer, C. & Gelenbe, E. (2000). Video quality and traffic QoS in learning-based subsampled and receiver-interpolated video sequences. IEEE Journal on Selected Areas in Communications 18(2): 150–167.CrossRefGoogle Scholar
17.Cramer, C., Gelenbe, E., & Gelenbe, P. (1998). Image and video compression. IEEE Potentials 17(1): 29–33.CrossRefGoogle Scholar
18.Donegan, M. (2011). Operators urge action against chatty apps. Light Reading Report, June 2011. [Online]. Available: http://www.lightreading.com/operators-urge-action-against-chatty-apps/d/d-id/687399Google Scholar
19.Ericsson. (2014). High availability is more than five nines. July 2014. [Online]. Available: http://www.ericsson.com/real-performance/wp-content/uploads/sites/3/2014/07/high-avaialbility.pdfGoogle Scholar
20.Ericsson. (2014). A smartphone app developer's guide: Optimizing for mobile networks. Whitepaper, April 2014. [Online]. Available: http://www.ericsson.com/res/docs/2014/smartphone-app-dev-guide.pdfGoogle Scholar
21.Francois, F., Abdelrahman, O.H., & Gelenbe, E. (2015). Impact of signaling storms on energy consumption and latency of LTE user equipment. In Proceedings of Seventh IEEE International Symposium on Cyberspace Safety and Security (CSS), New York, August 2015.CrossRefGoogle Scholar
22.Gabriel, C. (2012). DoCoMo demands Google's help with signalling storm. Rethink Wireless, January 2012. [Online]. Available: http://www.rethink-wireless.com/2012/01/30/docomo-demands-googles-signalling-storm.htmGoogle Scholar
23.Gelenbe, E. (1989). Random neural networks with negative and positive signals and product form solution. Neural Computation 1(4): 502–510, [Online]. Available: http://dx.doi.org/10.1162/neco.1989.1.4.502Google Scholar
24.Gelenbe, E. (1990). Stability of the random neural network model. Neural Computation 2(2): 239–247.Google Scholar
25.Gelenbe, E. (1993). Learning in the recurrent random neural network. Neural Computation 5(1): 154–164. [Online]. Available: http://dx.doi.org/10.1162/neco.1993.5.1.154Google Scholar
26.Gelenbe, E. (1994). G-networks: a unifying model for neural and queueing networks. Annals of Operations Research 48(5): 433–461. [Online]. Available: http://dx.doi.org/10.1007/BF02033314Google Scholar
27.Gelenbe, E. (2000). The first decade of G-networks. European Journal of Operational Research 126(2): 231–232. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0377221799004750Google Scholar
28.Gelenbe, E. & Abdelrahman, O.H. (2015). Countering mobile signaling storms with counters. In Proceedings of International Conference on Cyber PhysicaL Systems, IoT and Sensors Networks (Cyclone), Rome, Italy, October 2015.Google Scholar
29.Gelenbe, E., Bakircioglu, H., & Kocak, T. (1998). Image processing with the random neural network. pp. 38–49. [Online]. Available: http://dx.doi.org/10.1117/12.304658Google Scholar
30.Gelenbe, E., Feng, Y., & Krishnan, K. (1996). Neural network methods for volumetric magnetic resonance imaging of the human brain. Proceedings of the IEEE 84(10): 1488–1496.Google Scholar
31.Gelenbe, E. & Fourneau, J.-M. (1999). Random neural networks with multiple classes of signals. Neural Computation 11(4): 953–963, [Online]. Available: http://dx.doi.org/10.1162/089976699300016520Google Scholar
32.Gelenbe, E., Harmani, K., & Krolik, J. (1998). Learning neural networks for detection and classification of synchronous recurrent transient signals. Signal Processing 64(3): 233–247, [Online]. Available: http://www.sciencedirect.com/science/article/pii/S016516849700193XGoogle Scholar
33.Gelenbe, E. & Hussain, K. (2002). Learning in the multiple class random neural network. IEEE Transactions on Neural Networks 13(6): 1257–1267.CrossRefGoogle ScholarPubMed
34.Gelenbe, E., Koçak, T., & Wang, R. (2004). Wafer surface reconstruction from top-down scanning electron microscope images. Microelectronic Engineering 75(2): 216–233, [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0167931704003302CrossRefGoogle Scholar
35.Gelenbe, E. & Loukas, G. (2007). A self-aware approach to denial of service defence. Computer Networks 51(5): 1299–1314.Google Scholar
36.Gelenbe, E. & Morfopoulou, C. (2011). A framework for energy-aware routing in packet networks. Computer Journal 54(6): 850–859.CrossRefGoogle Scholar
37.Gelenbe, E., Sungur, M., Cramer, C., & Gelenbe, P. (1996). Traffic and video quality with adaptive neural compression. Multimedia Systems 4(6): 357–369, [Online]. Available: http://dx.doi.org/10.1007/s005300050037Google Scholar
38.Gelenbe, E. & Timotheou, S. (2008). Random neural networks with synchronized interactions. Neural Computation 20(9): 2308–2324, [Online]. Available: http://dx.doi.org/10.1162/neco.2008.04-07-509Google Scholar
39.Gorbil, G., Abdelrahman, O.H., & Gelenbe, E. (2014). Storms in mobile networks. In Proceedings of Tenth ACM Symposium on QoS and Security for Wireless and Mobile Networks (Q2SWinet), Montreal, Canada, September 2014, pp. 119–126.CrossRefGoogle Scholar
40.Gorbil, G., Abdelrahman, O.H., Pavloski, M., & Gelenbe, E. (2015). Modeling and analysis of RRC-based signalling storms in 3G networks. IEEE Transactions on Emerging Topics in Computing PP(99): 1, [Online]. Available: http://dx.doi.org/10.1109/TETC.2015.2389662Google Scholar
41.GSMA. (2014). Smarter apps for smarter phones, version 4.0. November 2014. [Online]. Available: http://www.gsma.com/newsroom/wp-content/uploads//TS-20-v4-0.pdfGoogle Scholar
42.Gupta, A., Verma, T., Bali, S., & Kaul, S. (2013). Detecting MS initiated signaling DDoS attacks in 3G/4G wireless networks. In Proceedings of Fifth International Conference on Communication Systems and Networks (COMSNETS), Bangalore, India, January 2013, pp. 1–6.CrossRefGoogle Scholar
43.Jiantao, S. (2012). Analyzing the network friendliness of mobile applications. Huawei, Technical Report, July 2012. [Online]. Available: http://www.huawei.com/ilink/en/download/HW_146595Google Scholar
44.Ksentini, A., Hadjadj-Aoul, Y., & Taleb, T. (2012). Cellular-based machine-to-machine: overload control. IEEE Network 26(6): pp. 54–60.Google Scholar
45.Lee, P.P., Bu, T., & Woo, T. (2007). On the detection of signaling DoS attacks on 3G wireless networks. In Proceedings of 26th IEEE International Conference on Computer Communications (INFOCOM), Anchorage, AK, USA, May 2007, pp. 1289–1297.CrossRefGoogle Scholar
46.Li, J., Pei, W., & Cao, Z. (2013). Characterizing high-frequency subscriber sessions in cellular data networks. In Proceedings of IFIP Networking Conference, Brooklyn, NY, May 2013, pp. 1–9.Google Scholar
47.Loukas, G. & Öke, G. (2010). Protection against denial of service attacks: a survey. Computer Journal 53(7): 1020–1037.CrossRefGoogle Scholar
48.Maslennikov, D. (2013). Mobile malware evolution: Part 6. Kaspersky Laboratory, Technical Report, February 2013. [Online]. Available: https://securelist.com/analysis/publications/36996/mobile-malware-evolution-part-6/Google Scholar
49.Mulliner, C., Liebergeld, S., Lange, M., & Seifert, J.-P. (2012). Taming Mr Hayes: mitigating signaling based attacks on smartphones. In Proceedings of 42nd Annual IEEE/IFIP Int'l Conference on Dependable Systems and Networks (DSN). Boston, MA: IEEE Computer Society, June 2012, pp. 1–12.Google Scholar
50.NSN Smart Labs. (2011). Understanding smartphone behavior in the network. White paper, January 2011. [Online]. Available: http://networks.nokia.com/system/files/document/nsn_smart_labs_white_paper.pdfGoogle Scholar
51.Öke, G. & Loukas, G. (2007). A denial of service detector based on maximum likelihood detection and the random neural network. Computer Journal 50(6): 717–727.Google Scholar
52.Oke, G., Loukas, G., & Gelenbe, E. (2007). Detecting denial of service attacks with bayesian classifiers and the random neural network. In Proceedings of Fuzzy Systems Conference (Fuzz-IEEE), London, UK, July 2007, pp. 1964–1969.CrossRefGoogle Scholar
53.Qian, F., Wang, Z., Gerber, A., Mao, Z.M., Sen, S., & Spatscheck, O. (2010). Characterizing radio resource allocation for 3G networks. In Proceedings of Tenth ACM Internet Measurement Conference (IMC), Melbourne, Australia, November 2010, pp. 137–150.Google Scholar
54.Qian, Z., Wang, Z., Xu, Q., Mao, Z.M., Zhang, M., & Wang, Y.-M. (2012). You can run, but you can't hide: Exposing network location for targeted DoS attacks in cellular networks. In Proceedings of Network and Distributed System Security Symp. (NDSS), San Diego, CA, February 2012, pp. 1–16.Google Scholar
55.Redding, G. (2013). OTT service blackouts trigger signaling overload in mobile networks. Nokia Solutions and Networks, September 2013. [Online]. Available: https://blog.networks.nokia.com/mobile-networks/2013/09/16/ott-service-blackouts-trigger-signaling-overload-in-mobile-networks/Google Scholar
56.Ricciato, F. (2006). Unwanted traffic in 3G networks. ACM SIGCOMM Computer Communications Reviews 36(2): 53–56.Google Scholar
57.Ricciato, F., Coluccia, A., & D'Alconzo, A. (2010). A review of DoS attack models for 3G cellular networks from a system-design perspective. Computer Communications 33(5): 551–558.Google Scholar
58.Serror, J., Zang, H., & Bolot, J.C. (2006). Impact of paging channel overloads or attacks on a cellular network. In Proceedings of Fifth ACM Workshop on Wireless Security (WiSe’06), LA, CA, September 2006, pp. 75–84.Google Scholar
59.Shafiq, M.Z., Ji, L., Liu, A.X., Pang, J., & Wang, J. (2012). A first look at cellular machine-to-machine traffic: Large scale measurement and characterization. SIGMETRICS Performance Evaluation Review 40(1): 65–76.Google Scholar
60.Telesoft Technologies. (2012). Mobile data monitoring. White paper, 2012.Google Scholar
61.Timotheou, S. (2010). The random neural network: A survey. Computer Journal 53(3): 251–267, [Online]. Available: http://comjnl.oxfordjournals.org/content/53/3/251.abstractGoogle Scholar
62.Traynor, P. et al. (2009). On cellular botnets: measuring the impact of malicious devices on a cellular network core. In Proceedings of 16th ACM Conference on Computer and Communications Security (CCS), Chicago, IL, pp. 223–234.CrossRefGoogle Scholar
63.Wang, Z., Qian, Z., Xu, Q., Mao, Z., & Zhang, M. (2011). An untold story of middleboxes in cellular networks. In Proceedings of ACM SIGCOMM, Toronto, Canada, August 2011, pp. 374–385.CrossRefGoogle Scholar