Dissertation > Excellent graduate degree dissertation topics show

Prediction of Network Attack Frequency Based on Chaotic Time Series

Author: LiuWenXing
Tutor: SuJinShu
School: National University of Defense Science and Technology
Course: Computer Science and Technology
Keywords: Frequency of attacks Chaotic time series Forecast Phase Space Reconstruction Lyapunov exponent Alternative data C-C False nearest point
CLC: TP393.08
Type: Master's thesis
Year: 2008
Downloads: 115
Quote: 4
Read: Download Dissertation

Abstract


Intrusion prevention technology in the traditional sense is to establish a security and defense systems, to prevent possible attacks by patching vulnerabilities, intrusion detection, firewall log detection system logs detection. These methods are often taken in the case of the attacks have occurred some stop-gap measure, more passive, and not timely and effective counter attack. If you can use some of the methods and measures to predict the scale and damage of the next attack is going to happen, the network security personnel early and work out effective preventive strategies to avoid loss in the attack; same time, relevant departments and personnel can also advance the implementation of counter-measures targeted attack before it blocked. This paper focuses on the chaotic characteristics of the research network attack frequency time series discrimination and forecast data characteristics distinguish the frequency of cyber attacks, and at the same time using a new method to more accurately predict the frequency of cyber attacks, especially large-scale attack. Dissertation research work is mainly focused on the following aspects: ① network attack frequency prediction Research, pointed out that the main reason for the slow progress in the current network attack frequency prediction: one is difficult to obtain a complete and continuous network attack frequency data existing prediction methods can not describe the frequency of data characteristics of cyber attacks. ② two phase space reconstruction parameters selection method - CC method and false nearest point method, and the the false nearest point method has been improved. The combination of the CC method and improved false nearest point method proposed a new phase space reconstruction parameter selection method - based on false nearest point of the CC method, its application to network attack frequency sequence of phase space reconstruction parameters selection, The validation of the method used to select the feasibility phase space reconstruction parameters. And ③ research and realized two complementary chaotic time series characteristics discriminating method - Lyapunov index method and surrogate data, verify the network attack frequency sequence chaos of these two methods. The ④ analysis special sequence of network attack frequency, point out the deficiencies of traditional error statistics to measure network attack frequency prediction error. A more appropriate error statistics based on the mean absolute percentage error (MAPE) - The weighted average absolute percentage error (WMAPE), actual error checking effect to verify WMAPE of superiority. ⑤ study four typical chaotic time series prediction method using these methods to predict the real network attack frequency sequence, and achieved good results. Selected two of the most suitable network attack frequency prediction methods - zero-order local law and RBF neural network method to forecast error statistics, and analysis of the applicable conditions of the two methods. ⑥ using statistical ARIMA model to predict the the real network attack frequency sequence verified, by comparison of the predicted effects of the ARIMA model and chaotic methods, chaotic time series forecasting method is more accurate than traditional statistical methods in the prediction of the frequency of cyber attacks.

Related Dissertations

  1. Application of Numerical Designing Cigarette Blending Formula on Computational Intelligence,TS44
  2. The Evaluation and Forecasting Research on Uncertainty Systems Method of Student Achievement,G642.4
  3. Research on the Evaluation of Straw Resource and the Development of Scale-Up Straw Energy Utilization in Jiangsu Province,S38
  4. Study on Growth Monitoring Technique Based on Pixel Un-Mixing Method and HJ Remote Sensing Images in Paddy Rice,S511
  5. The Research of Prediction of Lean Yield with CSB Image-Meater and Pork Carcass Grading System,S828
  6. With Delay fishing items and based on the ratio of prey - predator model,O175
  7. Research on Talents Team in Hefei-Wuhu-Bengbu Based on Independent Innovation,C964.2
  8. Expression of Chemokine Receptor CCR5 in Human Non-small-cell Lung Cancer,R734.2
  9. TV weather programs \,G222
  10. CC Oil Production Plant Optimization pay system,F426.22
  11. Zhaoguan Lower Coal Group water inrush prediction and control techniques,TD745
  12. Research on the Feasibility of Highway Construction Project,F542
  13. Analysis of China’s Household Electrical Appliance Industry Supply Chain Integration,F426.6
  14. Analysis on Synoptic Climatology Characteristics and Forecast Methods of Fog in Hainan,P457
  15. "OD Matrix Estimation" Technology in Urban Traffic Demand Forecast Prediction Research,U491.14
  16. Aircraft icing numerical prediction system design and implementation,TP311.52
  17. Applied Research of Ground Penetrating Radar in Tunnel Geological Prediction,U452.11
  18. Research on Operations Management Improvement of Natconn Company,F426.63
  19. Research on Low Power Techniques of the Instruction Fetching Unit in Embedded Processors,TP332
  20. Application of Rough Set and Flex in Mid-long Term Runoff Forecasting,P338
  21. The Comprehensive Research of Energy Consumption and CO2 Emission in Hubei Province,F426.2

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Computer network > General issues > Computer Network Security
© 2012 www.DissertationTopic.Net  Mobile