A Survey of Tools and Techniques for Web Attack Detection
DOI:
https://doi.org/10.54654/isj.v1i15.852Keywords:
Web attack, Web attack detection, Web attack detection based on signatures, Web attack detection based on machine learningTóm tắt
Abstract—Web attacks include types of attacks to websites and web applications to steal sensitive information, to possibly disrupt web-based service systems and even to take control of the web systems. In order to defend against web attacks, a number of tools and techniques have been developed and deployed in practice for monitoring, detecting and preventing web attacks to protect websites, web applications and web users. It is necessary to survey and evaluate existing tools and techniques for monitoring and detecting web attacks because this information can be used for the selection of suitable tools and techniques for monitoring and detecting web attacks for specific websites and web applications. In the first half, the paper surveys some typical tools and techniques for monitoring and detecting web attacks, which have been proposed and applied in practice. The paper’s later half presents the experiment and efficiency evaluation of a web attack detection model based on machine learning. Experimental results show that the machine learning based model for web attack detection produces a high detection accuracy of 99.57% and the model has the potential for practical deployment.
Tóm tắt—Tấn công web gồm các dạng tấn công vào các website và ứng dụng web nhằm đánh cắp các thông tin nhạy cảm, có thể gây ngưng trệ hệ thống dịch vụ, hoặc chiếm quyền kiểm soát hệ thống. Để phòng chống tấn công web, nhiều kỹ thuật và công cụ đã được nghiên cứu, phát triển và ứng dụng trong thực tế phục vụ giám sát, phát hiện và ngăn chặn dạng tấn công này nhằm bảo vệ các website, ứng dụng web và người dùng web. Việc khảo sát, đánh giá các công cụ và kỹ thuật giám sát, phát hiện tấn công web hiện có là cơ sở cho lựa chọn công cụ, kỹ thuật phát hiện tấn công web phù hợp cho các hệ thống website, ứng dụng web cụ thể. Trong phần đầu, bài báo này khảo sát một số công cụ và kỹ thuật giám sát, phát hiện tấn công web tiêu biểu đã được nghiên cứu, phát triển và ứng dụng trên thực tế. Phần sau của bài báo trình bày nội dung thử nghiệm, đánh giá hiệu quả của một mô hình phát hiện tấn công web dựa trên học máy. Các kết quả thử nghiệm cho thấy, mô hình phát hiện tấn công web dựa trên học máy cho độ chính xác đạt tới 99.57%, có tiềm năng triển khai hiệu quả trên thực tế.
Downloads
References
OWASP, Open Web Application Security Project, http://www.owasp.org, accessed 1.2021.
Hoàng Xuân Dậu, An toàn ứng dụng web và cơ sở dữ liệu, Học viện Công nghệ Bưu Chính Viễn Thông, 2017.
Hoang, X.D. Detecting Common Web Attacks Based on Machine Learning Using Weblog. K.-U. Sattler et al. (Eds.): ICERA 2020, LNNS 178, pp. 311–318, 2021.
VNCS – Giải pháp giám sát website tập trung, http://vncs.vn/portfolio/giai-phap-giam-satwebsites-tap-trung, accessed 1.2021.
Nagios Web Application Monitoring Software, https://www.nagios.com/solutions/webapplication-monitoring/, accessed 1.2021.
Site24x7, Website Defacement Monitoring, https://www.site24x7.com/monitorwebpagedefacement.html, accessed 1.2021.
Mod Security, https://www.modsecurity.org, accessed 1.2021.
Snort IDS, http://www.snort.org, accessed 1.2021.
Abhishek Kumar Baranwal, Approaches to detect SQL injection and XSS in web applications, EECE
B, Term Survey Paper, University of British Columbia, Canada, 2012.
OWASP ModSecurity Core Rule Set, https://www.owasp.org/index.php/Category: OWASP_ModSecurity_Core_Rule_Set_Project, accessed 1.2021.
Kemalis, K. and T. Tzouramanis. SQL-IDS: A Specification-based Approach for SQLinjection Detection. SAC’08. Fortaleza, Ceará, Brazil, ACM (2008), pp. 2153-2158.
P. Bisht, and V.N. Venkatakrishnan, “XSSGUARD: Precise dynamic prevention of Cross-Site Scripting Attacks,” In Proceeding of 5th Conference on Detection of Intrusions and Malware & Vulnerability Assessment, LNCS 5137, 2008, pp. 23-43.
Doyen Sahoo, Chenghao Liu, and Steven C.H. Hoi, Malicious URL Detection using Machine Learning: A Survey, https://arxiv.org/abs/1701.07179, Mar 2017.
Gustavo Betarte, Eduardo Giménez, Rodrigo Martínez, and Álvaro Pardo, Machine learningassisted virtual patching of web applications, https://arxiv.org/abs/1803.05529, Mar 2018.
Carmen Torrano-Gimenez, Alejandro PérezVillegas and Gonzalo Alvarez, An Anomaly-Based Approach for Intrusion Detection in Web Traffic, published by The Allen Institute for Artificial Intelligence, 2009.
Jingxi Liang, Wen Zhao and Wei Ye. “AnomalyBased Web Attack Detection: A Deep Learning Approach”. ICNCC 2017, Kunming, China, December 8-10, 2017.
Yao Pan, Fangzhou Sun, Zhongwei Teng, Jules White, Douglas C. Schmidt, Jacob Staples and Lee Krause. “Detecting web attacks with end-to-end deep learning”. Journal of Internet Services and Applications (2019) 10:16, SpringerOpen.
HTTP DATASET CSIC 2010, https://www.isi. csic.es/dataset/, accessed 1.2021.
HTTP Param Dataset, https://github.com/ Morzeux/ HttpParamsDataset, accessed 1.2021.
A. Smola and S.V.N. Vishwanathan, “Introduction to Machine Learning,” Cambridge University, 2008.
Downloads
Published
How to Cite
Issue
Section
License
Proposed Policy for Journals That Offer Open Access
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Proposed Policy for Journals That Offer Delayed Open Access
Authors who publish with this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication, with the work [SPECIFY PERIOD OF TIME] after publication simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
