引
言
随着互联网和大数据的快速发展,网络异常检测作为保护网络安全和维护系统正常运行的手段变得越来越重要。网络异常检测往往依靠日志或流量等网络数据,而这些数据发生概念漂移会对网络异常检测的准确性和可靠性产生较为严重的影响。因此,近年来针对网络异常检测领域的概念漂移检测研究也引起了广泛关注。概念漂移(Concept Drift)是指随着时间推移,流数据的分布发生变化的情况,这种变化可能由外部或内部因素引起。网络异常检测领域常用到的数据有日志数据和流量数据等,本质上也是流数据。因此,已有的针对流数据的概念漂移检测方法也适用于网络异常检测领域。
1
概念漂移概述
数据发生概念漂移的原因可能有多种:
2
概念漂移分类
图1 基于真伪的两种概念漂移抽象化描述
图2 基于速度的四种概念漂移抽象化描述
图3 基于真伪的两种概念漂移抽象化描述
3
概念漂移检测方法
图4 ARF自适应框架工作流程
(a) Type-LDA框架流程图
(b) Type-LDA框架中漂移类型识别器模块工作示意图
(c) Type-LDA框架中漂移点定位器模块工作示意图
图5 Type-LDA框架流程图及主要模块工作示意图
(2)Guo等人[16]提出了一种基于选择性集成的在线自适应深度神经网络(SEOA)来解决概念漂移问题。首先,通过将浅层特征与深层特征相结合来构建自适应深度单元,并根据相邻时刻网络数据的变化自适应地控制神经网络中的信息流,从而提高了在线深度学习模型的收敛性,将不同层的自适应深度单元作为基础分类器进行集成,并根据每个分类器的损失进行动态加权,以更好地检测概念漂移。
总
结
参考文献
[1] João Gama, Indre Žliobait ˙ e, Albert Bifet, Mykola Pechenizkiy, and Abdelhamid Bouchachia. 2014. A survey on concept drift adaptation. ACM Computing Surveys 46, 4 (2014), 1–37.
[2] LECHNER A, KECKEIS H, HUMPHRIES P. Patterns and processes in the drift of early developmental stages of fish in rivers: a review[J]. Reviews in Fish Biology and Fisheries, 2016, 26: 471-489.
[3] DIEHL S, ANDERSON K E, NISBET R M. Population responses of drifting stream invertebrates to spatial environmental variability: an emerging conceptual framework[M] // Aquatic insects: challenges to populations. Wallingford UK: CABI, 2008: 158-183.
[4] COHEN A M, BHUPATIRAJU R T, HERSH W R. Feature generation, feature selection, classifiers, and conceptual drift for biomedical document triage[C]//TREC. 2004.
[5] BAYRAM F, AHMED B S, KASSLER A. From concept drift to model degradation: An overview on performance-aware drift detectors[J]. Knowledge-Based Systems, 2022, 245: 108632.
[6] KORYCKI Ł, KRAWCZYK B. Concept drift detection from multi-class imbalanced data streams[C]//2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 2021: 1068-1079.
[7] ALKAYEM N F, CAO M, ZHANG Y, et al. Structural damage detection using finite element model updating with evolutionary algorithms: a survey[J]. Neural Computing and Applications, 2018, 30: 389-411.
[8] LU J, LIU A, DONG F, et al. Learning under concept drift: A review[J]. IEEE transactions on knowledge and data engineering, 2018, 31(12): 2346-2363.
[9] BAYRAM F, AHMED B S, Kassler A. From concept drift to model degradation: An overview on performance-aware drift detectors[J]. Knowledge-Based Systems, 2022, 245: 108632.
[10] DRIES A, RÜCKERT U. Adaptive concept drift detection[J]. Statistical Analysis and Data Mining: The ASA Data Science Journal, 2009, 2(5‐6): 311-327.
[11] NISHIDA K, YAMAUCHI K. Detecting concept drift using statistical testing[C]//International conference on discovery science. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007: 264-269.
[12] HAYAT M Z, BASIRI J, SEYEDHOSSEIN L, et al. Content-based concept drift detection for email spam filtering[C]//2010 5th International Symposium on Telecommunications. IEEE, 2010: 531-536.
[13] Sugandh Seth, Kuljit Kaur Chahal, Gurvinder Singh, Concept Drift–Based Intrusion Detection For Evolving Data Stream Classification In IDS: Approaches And Comparative Study, The Computer Journal, 2024.
[14] J Li, H Yu, Z Zhang, X Luo, S Xie , Concept Drift Adaptation by Exploiting Drift Type, ACM Transactions on Knowledge Discovery from Data, 2024.
[15] ELWELL R, POLIKAR R. Incremental learning of concept drift in nonstationary environments[J]. IEEE Transactions on Neural Networks, 2011, 22(10): 1517-1531.
[16] GUO H, ZHANG S, WANG W. Selective ensemble-based online adaptive deep neural networks for streaming data with concept drift[J]. Neural Networks, 2021, 142: 437-456.
中国保密协会科学技术分会
作者:中国科学院计算机网络信息中心 杜冠瑶 郭勇杰
责编:何洁
2023年精彩文章TOP5回顾
近期精彩文章回顾
推荐站内搜索:最好用的开发软件、免费开源系统、渗透测试工具云盘下载、最新渗透测试资料、最新黑客工具下载……
还没有评论,来说两句吧...