An Attack Detection Framework Based on BERT and Deep Learning

被引:23
作者
Seyyar, Yunus Emre [1 ]
Yavuz, Ali Gokhan [2 ]
Unver, Halil Murat [1 ]
机构
[1] Kirikkale Univ, Grad Sch Nat & Appl Sci, Dept Comp Engn, TR-71451 Kirikkale, Turkey
[2] Turkish German Univ, Grad Sch Nat & Appl Sci, Dept Comp Engn, TR-34820 Istanbul, Turkey
关键词
Protocols; Bit error rate; Natural language processing; Uniform resource locators; Structured Query Language; Firewalls (computing); Deep learning; Anomalous request; BERT; deep learning; web attack; multilayer perceptron; natural language processing;
D O I
10.1109/ACCESS.2022.3185748
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Deep Learning (DL) and Natural Language Processing (NLP) techniques are improving and enriching with a rapid pace. Furthermore, we witness that the use of web applications is increasing in almost every direction in parallel with the related technologies. Web applications encompass a wide array of use cases utilizing personal, financial, defense, and political information (e.g., wikileaks incident). Indeed, to access and to manipulate such information are among the primary goals of attackers. Thus, vulnerability of the information targeted by adversaries is a vital problem and if such information is captured then the consequences can be devastating, which can, potentially, become national security risks in the extreme cases. In this study, as a remedy to this problem, we propose a novel model that is capable of distinguishing normal HTTP requests and anomalous HTTP requests. Our model employs NLP techniques, Bidirectional Encoder Representations from Transformers (BERT) model, and DL techniques. Our experimental results reveal that the proposed approach achieves a success rate over 99.98% and an F1 score over 98.70% in the classification of anomalous and normal requests. Furthermore, web attack detection time of our model is significantly lower (i.e., 0.4 ms) than the other approaches presented in the literature.
引用
收藏
页码:68633 / 68644
页数:12
相关论文
共 50 条
[31]   A Phishing-Attack-Detection Model Using Natural Language Processing and Deep Learning [J].
Benavides-Astudillo, Eduardo ;
Fuertes, Walter ;
Sanchez-Gordon, Sandra ;
Nunez-Agurto, Daniel ;
Rodriguez-Galan, German .
APPLIED SCIENCES-BASEL, 2023, 13 (09)
[32]   Hybrid Deep Learning Based Attack Detection for Imbalanced Data Classification [J].
Almarshdi, Rasha ;
Nassef, Laila ;
Fadel, Etimad ;
Alowidi, Nahed .
INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2023, 35 (01) :297-320
[33]   Deep-Learning-Based Approach for IoT Attack and Malware Detection [J].
Tasci, Burak .
APPLIED SCIENCES-BASEL, 2024, 14 (18)
[34]   Deep Learning-Based Attack Detection and Classification in Android Devices [J].
Gomez, Alfonso ;
Munoz, Antonio .
ELECTRONICS, 2023, 12 (15)
[35]   Deep learning-based classification model for botnet attack detection [J].
Abdulghani Ali Ahmed ;
Waheb A. Jabbar ;
Ali Safaa Sadiq ;
Hiran Patel .
Journal of Ambient Intelligence and Humanized Computing, 2022, 13 :3457-3466
[36]   A deep learning based intelligent framework to mitigate DDoS attack in fog environment [J].
Priyadarshini, Rojalina ;
Barik, Rabindra Kumar .
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES, 2022, 34 (03) :825-831
[37]   Anomaly-Based Web Attack Detection: A Deep Learning Approach [J].
Liang, Jingxi ;
Zhao, Wen ;
Ye, Wei .
PROCEEDINGS OF 2017 VI INTERNATIONAL CONFERENCE ON NETWORK, COMMUNICATION AND COMPUTING (ICNCC 2017), 2017, :80-85
[38]   Deep learning-based classification model for botnet attack detection [J].
Ahmed, Abdulghani Ali ;
Jabbar, Waheb A. ;
Sadiq, Ali Safaa ;
Patel, Hiran .
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2020, 13 (7) :3457-3466
[39]   Support attack detection algorithm for recommendation system based on deep learning [J].
Li, Xin ;
Wang, Zhixiao .
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING, 2023, 2023 (01)
[40]   Deep Learning Poison Data Attack Detection [J].
Chacon, Henry ;
Silva, Samuel Henrique ;
Rad, Paul .
2019 IEEE 31ST INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI 2019), 2019, :971-978