creator Chen, Ying advisor Cheng, Yu It is easy for the malicious nodes to take advantage of CSMA/CA based wireless protocols to gain unfair larger share of the network throughput because of the distributed nature of the IEEE 802.11 distributed coordination function (DCF). The backoff misbehavior will happen when one node deliberately chooses smaller backoff parameters. This paper adopts a promising non-parametric cumulative sum test (CUSUM) based scheme to quickly find abrupt changes in a process without prior knowledge of the statistics of the change occurrences. According to a Markov chain based analytical model, we can systematically study the real-time misbehavior detection results from CUSUM based method, thus quantitatively computer the system configuration parameters for guaranteed performance in terms of average false positive rate, average detection delay, and missed detection ratio. Submitted by Lance Garrison (garrlanc@my.dom.edu) on 2012-03-07T03:16:53Z No. of bitstreams: 2 Thesis_Ying Chen.pdf: 646940 bytes, checksum: 802a8c43adf335d813db10186072dd54 (MD5) Signed cover.pdf: 25270 bytes, checksum: 7afcccfad3325ec1ac1af516c7c65486 (MD5) Made available in DSpace on 2012-03-07T03:16:53Z (GMT). No. of bitstreams: 2 Thesis_Ying Chen.pdf: 646940 bytes, checksum: 802a8c43adf335d813db10186072dd54 (MD5) Signed cover.pdf: 25270 bytes, checksum: 7afcccfad3325ec1ac1af516c7c65486 (MD5) Previous issue date: 2011-07 M.S. in Computer Engineering, July 2011 2011-07 2011-07 http://hdl.handle.net/10560/2550 en Thesis born digital application/pdf In Copyright http://rightsstatements.org/page/InC/1.0/ Restricted Access ECE / Electrical and Computer Engineering Illinois Institute of Technology Affiliated department