基于抽样流长与完全抽样阈值的异常流自适应抽样算法

伊鹏; 钱坤; 黄万伟; 王晶; 张震

doi:10.11999/JEIT141379

基于抽样流长与完全抽样阈值的异常流自适应抽样算法

doi: 10.11999/JEIT141379

伊鹏¹,
钱坤¹,
黄万伟¹,
王晶¹,
张震¹

基金项目:

国家973计划项目(2012CB315901, 2013CB329104)

计量
- 文章访问数: 1256
- HTML全文浏览量: 123
- PDF下载量: 1187
- 被引次数: 0
出版历程
- 收稿日期: 2014-10-29
- 修回日期: 2015-01-13
- 刊出日期: 2015-07-19

Adaptive Flow Sampling Algorithm Based on Sampled Packets and Force Sampling Threshold S Towards Anomaly Detection

摘要

摘要: 高速IP网络的流量测量与异常检测是网络测量领域研究的热点。针对目前网络流量测量算法对小流估计精度偏低，对异常流量筛选能力较差的缺陷，该文提出一种基于业务流已抽样长度与完全抽样阈值S的自适应流抽样算法(AFPT)。AFPT算法根据完全抽样阈值S筛选对异常流量敏感相关的小流，同时根据业务流已抽样长度自适应调整抽样概率。仿真和实验结果表明，AFPT算法的估计误差与理论上界相符，具有较强的异常流量筛选能力，能够有效提高异常检测算法的准确率。
- 网络测量 /
- 自适应流抽样 /
- 异常检测
Abstract: The network traffic measurement and anomaly detection for high-speed IP network become the hotspot research of network measurement field. Because the current measurement algorithms have large estimation error for the mice flows and poor performance for the sampling anomaly traffic, an Adaptive Flow sampling algorithm based on the sampled Packets and force sampling Threshold S (AFPT) is proposed. According to the force sampling threshold S, the AFPT is able to sample the mice flows which is sensitive to the anomaly traffic, while adaptive adjustment the probability of sampling based on the sampled packets. The simulation and experimental results show that the estimation error of AFPT is consistent with the theoretical upper bound, and provide better performance for the anomaly traffic sampled. The proposed algorithm can effectively improve the accuracy of anomaly detection algorithm.

HTML全文

参考文献(15)

Zhou Ai-ping, Cheng Guang, and Guo Xiao-jun. High-speed network traffic measurement method[J]. Journal of Software, 2014, 25(1): 135-153.

Peter Lieven and Bj?rnScheuermann. High-speed per-flow traffic measurement with probabilistic multiplicity counting [C]. Proceedings of the INFOCOM 2010, San Diego, CA, USA, 2010: 1-9.

Cheng Guang and Tang Yong-ning. Estimation algorithms of the flow number from sampled packets on approximate approaches[J]. Journal of Software, 2013, 24(2): 255-265.

Lee Y J, Yeh Y R, and Wang Y C F. Anomaly detection via online oversampling principal component analysis[J]. IEEE Transactions on Knowledge and Data Engineering, 2013, 25(7): 1460-1470.

Pham D S, Venkatesh S, Lazarescu M, et al.. Anomaly detection in large-scale data stream networks[J]. Data Mining and Knowledge Discovery, 2014, 28(1): 145-189.

Cai Yuan-jun, Wu Bin, Zhang Xin-wei, et al.. Flow identification and characteristics mining from internet traffic with hadoop[C]. Proceedings of the Computer Information and Telecommunication Systems (CITS), Jeju Island, Korea, 2014: 1-5.

Brauckhoff D, Tellenbach B, Wagner A, et al.. Impact of packet sampling on anomaly detection metrics[C]. Proceedings. of the 6th ACM Sigcomm conference on Internet measurement, Rio de Janeiro, Brazil, 2006: 159-164.

Mai Jian-ning, Chuah C N, Sridharan A, et al.. Is sampled data sufficient for anomaly detection?[C]. Proceedings of the 6th ACM Sigcomm Conference on Internet Measurement, Rio de Janeiro, Brazil, 2006: 165-176.

Kumar A and Xu J. Sketch guided sampling using on-line estimates of flow size for adaptive data collection[C]. Proceedings of IEEE INFOCOM 2006, Barcelona, Spain, 2006: 1-11.

Li Tao and Chen Shi-gang. Per-flow traffic measurement through randomized counter sharing[J]. IEEE ACM Transactions on Networking, 2012, 13(5): 325-336.

王苏南. 高速复杂网络环境下异常流量检测技术研究[D]. [博士论文], 信息工程大学, 2012:38-49.

Wang Su-nan. Research on anomaly detection technology in high-speed complex network environment[D]. [Ph.D. dissertation], The PLA Information Engineering University, 2012: 38-49.

郭通. 基于自适应流抽样测量的网络异常检测技术研究[D]. [博士论文], 信息工程大学, 2013: 38-49.

Guo Tong. Research on network anomaly detection technology based on adaptive flow sampling measurement[D]. [Ph.D. dissertation], The PLA Information Engineering University, 2013: 38-49.

Lakhina A, Crovella M, and Diot C. Mining anomalies using traffic feature distributions[C]. Proceedings of the 5th ACM Sigcomm Conference on Internet Measurement, Philadelphia, PA, USA, 2005: 217-228.

施引文献

资源附件(0)

访问统计