期刊文献+

PU学习技术在Web入侵检测中的应用研究

原文传递
导出
摘要 传统Web入侵检测技术存在泛化能力差、入侵行为特征提取难等局限性,而且当存在大量无标记样本时检测能力较差;PU学习方法可以充分利用大量无标注样本完成Web入侵检测。本文从分析入侵行为及提取Web入侵行为的特征出发,提出一种基于PU学习的Web入侵检测方法,能够在标注样本少、存在大量无标记样本的情况下,有效地提高Web入侵检测能力。
作者 姜文秀
出处 《网络安全技术与应用》 2023年第8期35-37,共3页 Network Security Technology & Application
  • 相关文献

参考文献8

二级参考文献83

  • 1杨智君,田地,马骏骁,隋欣,周斌.入侵检测技术研究综述[J].计算机工程与设计,2006,27(12):2119-2123. 被引量:46
  • 2Murthy G, Liu B. Mining opinions in comparative sentences [C] //Proe of the 22nd Int Conf on Computational Linguistics (COLOING'08). NewYork ACM, 2008 241-248.
  • 3Hu Mingqing, Liu Bing. Mining opinion features in customer reviews [C] //Proc of the 19th National Conf on Artificial Intelligence(AAAI'04). San Jose: American Association for Artificial Intelligence, 2004:775-760.
  • 4Nitin J, Liu B. Opinion spam and analysis [C] //Proc of the 1st ACM Int Conf on Web Search and Data Mining (WSDM'08). New York: ACM, 2008:137-142.
  • 5Myle O, Choi Y L, Claire C, et al. Finding deceptive opinion spam by any stretch of the imagination [C] //Proc of the 49th Annual Meeting of the Association for Computational Linguistics Human Language Technologies ( ACL'11 ). Stroudshurg, PA Association for Computational Linguistics, 2011:309-319.
  • 6Li Fangtao, Huang Minlie, Yang Yi, et al. Learning to identify review spare [C] //Proc of the 22nd Int Joint Conf on Artificial Intelligence (IJCAI'2011). San Francisco.- Morgan Kaufmann, 2011:2488-2493.
  • 7Feng S, Ritwik B, Choi Y J. Syntactic stylometry for deception detection [C] //Proc of the 50th Annual Meeting of the Association for Computational Linguistics (ACL'12). Stroudsburg, PA Association for Computational Linguistics, 2012:171-175.
  • 8Liu B, Wee S L, Philip S Y, et el. Partially supervised classification of text documents [C] //Proc of the 19th Int Conf on Machine Learning (ICML'02). New York: ACM, 2002 387-394.
  • 9Charles E, Keith N. Learning classifiers from only positive and unlabeled data [C] //Proc of the 14th ACM SIGKDD Int Conf on Knowledge Discovery and Data Ming(SIGKDD'08). New York: ACM, 2008 213-220.
  • 10Li X L, Philip S Y, Liu B, et el. Positive unlabeled learning for data stream classification [C] //Proc of the 9th SIAM Int Conf on Data Ming (SDM'09). Philadelphia, PA= SIAM, 2009 .. 257-268.

共引文献52

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部