摘要
在全球网络信息化程度高速发展的大背景下,网络安全威胁不断进化和变化,攻击手段也在日益复杂化。尤其是尚未被安全研究人员或防御措施所知晓的网络攻击(即未知攻击,或称零日攻击或新型攻击)给网络安全带来了难以预测的威胁。未知攻击检测一直以来都是网络安全中的一个重要的课题,为了应对未知攻击的挑战,学术界和工业界提出了许多基于统计知识以及基于机器学习、深度学习等人工智能技术的方法来检测未知攻击。本文主要回顾了现有的未知攻击检测方面的研究,并对现有的研究成果进行了分析和总结,探讨了其中的优势和局限性,并对未知攻击检测的未来进行了展望。
1
引言
2
未知攻击检测方法
3
方法优缺点分析
表 1 未知攻击检测技术优缺点对比
4
总 结
参考文献
[1]Guo Y. A review of Machine Learning-based zero-day attack detection: Challenges and future directions[J]. Computer communications, 2023, 198: 175-185.
[2]Vukalović J, Delija D. Advanced persistent threats-detection and defense[C]//2015 38Th international convention on information and communication technology, electronics and microelectronics (MIPRO). IEEE, 2015: 1324-1330.
[3] Libicki M C, Ablon L, Webb T. The defender’s dilemma: Charting a course toward cybersecurity[M]. Rand Corporation, 2015.
[4]Schüppen S, Teubert D, Herrmann P, et al. {FANCI}: Feature-based automated {NXDomain} classification and intelligence[C]//27th USENIX Security Symposium (USENIX Security 18). 2018: 1165-1181.
[5]Fu C, Li Q, Shen M, et al. Realtime robust malicious traffic detection via frequency domain analysis[C]//Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. 2021: 3431-3446.
[6] Vu L, Nguyen Q U, Nguyen D N, et al. Learning latent representation for iot anomaly detection[J]. IEEE Transactions on Cybernetics, 2020, 52(5): 3769-3782.
[7]Ayoade G, Akbar K A, Sahoo P, et al. Evolving advanced persistent threat detection using provenance graph and metric learning[C]//2020 IEEE Conference on Communications and Network Security (CNS). IEEE, 2020: 1-9.
[8]Zhan M, Li Y, Yang X, et al. NSAPs: A novel scheme for network security state assessment and attack prediction[J]. Computers & Security, 2020, 99: 102031.
[9]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.
[10]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.
[11]Tang R, Yang Z, Li Z, et al. Zerowall: Detecting zero-day web attacks through encoder-decoder recurrent neural networks[C]//IEEE INFOCOM 2020-IEEE Conference on Computer Communications. IEEE, 2020: 2479-2488.
[12]Wan Y, Xu K, Xue G, et al. Iotargos: A multi-layer security monitoring system for internet-of-things in smart homes[C]//IEEE INFOCOM 2020-IEEE Conference on Computer Communications. IEEE, 2020: 874-883.
[13]Yang J, Chen X, Chen S, et al. Conditional variational auto-encoder and extreme value theory aided two-stage learning approach for intelligent fine-grained known/unknown intrusion detection[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 3538-3553.
[14]Blaise A, Bouet M, Conan V, et al. Detection of zero-day attacks: An unsupervised port-based approach[J]. Computer Networks, 2020, 180: 107391.
[15]Liu A, Wang Y, Li T. SFE-GACN: A novel unknown attack detection under insufficient data via intra categories generation in embedding space[J]. Computers & Security, 2021, 105: 102262.
[16]Heartfield R, Loukas G, Bezemskij A, et al. Self-configurable cyber-physical intrusion detection for smart homes using reinforcement learning[J]. IEEE Transactions on Information Forensics and Security, 2020, 16: 1720-1735.
[17]Finn C, Abbeel P, Levine S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//International conference on machine learning. PMLR, 2017: 1126-1135.
[18]Ravi S, Larochelle H. Optimization as a model for few-shot learning[C]//International conference on learning representations. 2016.
[19]Wang T, Lv Q, Hu B, et al. A few-shot class-incremental learning approach for intrusion detection[C]//2021 International Conference on Computer Communications and Networks (ICCCN). IEEE, 2021: 1-8.
[20]Rong C, Gou G, Hou C, et al. Umvd-fsl: Unseen malware variants detection using few-shot learning[C]//2021 international joint conference on neural networks (IJCNN). IEEE, 2021: 1-8.
[21]Chowdhury M M U, Hammond F, Konowicz G, et al. A few-shot deep learning approach for improved intrusion detection[C]//2017 IEEE 8th Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (UEMCON). IEEE, 2017: 456-462.
[22]Feng M, Xu H. Deep reinforecement learning based optimal defense for cyber-physical system in presence of unknown cyber-attack[C]//2017 IE2EE Symposium Series on Computational Intelligence (SSCI). IEEE, 2017: 1-8.
[23]Zanero S, et al. Unsupervised anomaly detection for network intrusion detection: An empirical comparison of seven methods. Computers & Security, 2018, 78: 245-259.
[24]Kim H, et al. Long short-term memory based intrusion detection system with feature selection. Computers & Electrical Engineering, 2019, 77: 48-58.
[25]Tang X, et al. A software-defined network intrusion detection method based on convolutional neural network. IEEE Access, 2019, 7: 39955-39967.
[26]Sab M, et al. Anomaly detection using fuzzy logic and genetic algorithm in KDD intrusion detection dataset. Journal of Network and Computer Applications, 2016, 73: 1-12.
[27]Ghandi S H, et al. Anomaly detection using deep belief networks with multi-objective evolutionary algorithm. Soft Computing, 2020, 24: 8439-8459.
[28]Wu J, et al. A Novel Threat Prediction Framework for Network Security. IEEE Transactions on Information Forensics and Security, 2020, 15: 2331-2344.
[29]Du H, Liu D F, Holsopple J, et al. Toward ensemble characterization and projection of multistage cyber attacks[C]//2010 Proceedings of 19th International Conference on Computer Communications and Networks. IEEE, 2010: 1-8.
[30]Luo S, Wu J, Li J, et al. A multi-stage attack mitigation mechanism for software-defined home networks[J]. IEEE Transactions on Consumer Electronics, 2016, 62(2): 200-207.
[31]Saud Z, Islam M H. Towards proactive detection of advanced persistent threat (apt) attacks using honeypots[C]//Proceedings of the 8th International Conference on Security of Information and Networks. 2015: 154-157.
[32]Fan W, Du Z, Smith-Creasey M, et al. Honeydoc: an efficient honeypot architecture enabling all-round design[J]. IEEE journal on selected areas in communications, 2019, 37(3): 683-697.
[33]Hakim M A, Aksu H, Uluagac A S, et al. U-pot: A honeypot framework for upnp-based iot devices[C]//2018 IEEE 37th International Performance Computing and Communications Conference (IPCCC). IEEE, 2018: 1-8.
[34]Krueger T, Gascon H, Krämer N, et al. Learning stateful models for network honeypots[C]//Proceedings of the 5th ACM workshop on Security and artificial intelligence. 2012: 37-48.
[35]Han W, Xue J, Wang Y, et al. APTMalInsight: Identify and cognize APT malware based on system call information and ontology knowledge framework[J]. Information Sciences, 2021, 546: 633-664.
[36]Paccagnella R, Datta P, Hassan W U, et al. Custos: Practical tamper-evident auditing of operating systems using trusted execution[C]//Network and distributed system security symposium. 2020.
中国保密协会
科学技术分会
长按扫码关注我们
作者:黄曦 中国科学院计算机网络信息中心
责编:夏天
2023年精彩文章TOP5回顾
近期精彩文章回顾
原文始发于微信公众号(中国保密协会科学技术分会):未知攻击检测技术研究简述
- 左青龙
- 微信扫一扫
-
- 右白虎
- 微信扫一扫
-
评论