Analyzing fusion of regularization techniques in the deep learning‐based intrusion detection system

Thakkar, Ankit; Lohiya, Ritika

doi:10.1002/int.22590

Cited by 21 publications

(5 citation statements)

References 75 publications

(191 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The highest accuracy achieved on CICIDS2017 dataset was 98.93% with XGboost. A fusion of regularization techniques is applied in [20], for increasing a DNN-based IDS performance, by using several datasets, including CICIDS2017.…”

Section: Related Workmentioning

confidence: 99%

New Denial of Service Attacks Detection Approach Using Hybridized Deep Neural Networks and Balanced Datasets

Mjahed¹,

Hadaj²,

Guarmah³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Denial of Service (DoS/DDoS) intrusions are damaging cyberattacks, and their identification is of great interest to the Intrusion Detection System (IDS). Existing IDS are mainly based on Machine Learning (ML) methods including Deep Neural Networks (DNN), but which are rarely hybridized with other techniques. The intrusion data used are generally imbalanced and contain multiple features. Thus, the proposed approach aims to use a DNN-based method to detect DoS/DDoS attacks using CICIDS2017, CSE-CICIDS2018 and CICDDoS 2019 datasets, according to the following key points. a) Three imbalanced CICIDS2017-2018-2019 datasets, including Benign and DoS/DDoS attack classes, are used. b) A new technique based on K-means is developed to obtain semi-balanced datasets. c) As a feature selection method, LDA (Linear Discriminant Analysis) performance measure is chosen. d) Four metaheuristic algorithms, counting Artificial Immune System (AIS), Firefly Algorithm (FA), Invasive Weeds Optimization (IWO) and Cuckoo Search (CS) are used, for the first time together, to increase the performance of the suggested DNN-based DoS attacks detection. The experimental results, based on semi-balanced training and test datasets, indicated that AIS, FA, IWO and CS-based DNNs can achieve promising results, even when cross-validated. AIS-DNN yields a tested accuracy of 99.97%, 99.98% and 99.99%, for the three considered datasets, respectively, outperforming performance established in several related works.

show abstract

Section: Related Workmentioning

confidence: 99%

New Denial of Service Attacks Detection Approach Using Hybridized Deep Neural Networks and Balanced Datasets

Mjahed¹,

Hadaj²,

Guarmah³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…On the other hand, researching and testing IDSs on incomplete datasets may yield inaccurate results [43], as shown in Ref. [44] in the case wherein these datasets are unbalanced. To address imbalance in training data, researchers focus on feature selection specifically, as in [43,45,46].…”

Section: Related Workmentioning

confidence: 99%

“…In UNSW-NB15, the network traffic is categorized into ten different types, including normal traffic, and nine attacks (e.g., fuzzers, analysis, backdoors, DoS, exploits, generic, reconnaissance, shellcode, and worms). In more detail, the normal traffic has 2,218,761 records and overwhelms attack traffic, which has 24,246,2677,2329,16,535,44,525,21,5481,13,987,1511, and 174 records for fuzzers, analysis, backdoors, DoS, exploits, generic, reconnaissance, shellcode, and worms, respectively.…”

Section: Experimental Datasets and Evaluation Metricmentioning

confidence: 99%

IMIDS: An Intelligent Intrusion Detection System against Cyber Threats in IoT

Nguyen

Tran

et al. 2022

Electronics

View full text Add to dashboard Cite

The increasing popularity of the Internet of Things (IoT) has significantly impacted our daily lives in the past few years. On one hand, it brings convenience, simplicity, and efficiency for us; on the other hand, the devices are susceptible to various cyber-attacks due to the lack of solid security mechanisms and hardware security support. In this paper, we present IMIDS, an intelligent intrusion detection system (IDS) to protect IoT devices. IMIDS’s core is a lightweight convolutional neural network model to classify multiple cyber threats. To mitigate the training data shortage issue, we also propose an attack data generator powered by a conditional generative adversarial network. In the experiment, we demonstrate that IMIDS could detect nine cyber-attack types (e.g., backdoors, shellcode, worms) with an average F-measure of 97.22% and outperforms its competitors. Furthermore, IMIDS’s detection performance is notably improved after being further trained by the data generated by our attack data generator. These results demonstrate that IMIDS can be a practical IDS for the IoT scenario.

show abstract

“…Shmalo et al 38 investigated the spectrum of weight layers using techniques from random matrix theory and determined that singular values should be removed during training to reduce overfitting and improve accuracy. To address overfitting issues encountered by deep learning techniques as a result of complex network structures, Thakkar et al 39 combined regularization and dropout effectively, improving the problem of deep learning overfitting. Some studies in other fields have reported that methods such as regularization 40,41 and data augmentation can alleviate the overfitting phenomenon to some extent.…”

Section: Introductionmentioning

confidence: 99%

EResNet‐SVM: an overfitting‐relieved deep learning model for recognition of plant diseases and pests

Xiong,

Li,

Wang

et al. 2024

J Sci Food Agric

View full text Add to dashboard Cite

BACKGROUNDThe accurate recognition and early warning for plant diseases and pests are a prerequisite of intelligent prevention and control for plant diseases and pests. Due to the phenotype similarity of the hazarded plant after plant diseases and pests occur as well as the interference of the external environment, traditional deep learning models often face the overfitting problem in phenotype recognition of plant diseases and pests, which leads to not only slow convergence speed of the network but also low recognition accuracy.RESULTSMotivated by the above problems, this paper proposes a deep learning model EResNet‐SVM to alleviate the overfitting for the recognition and classification of plant diseases and pests. First, the feature extraction capability of the model is improved by increasing feature extraction layers in the convolutional neural network (CNN). Second, the order‐reduced modules are embedded and a sparsely activated function is introduced to reduce model complexity and alleviate overfitting. Finally, a classifier fused by support vector machine (SVM) and fully connected layers (FC) are introduced to transforms the original nonlinear classification problem into a linear classification problem in high‐dimensional space to further alleviate the overfitting and improve the recognition accuracy of plant diseases and pests. The ablation experiments further demonstrate that the fused structure can effectively alleviate the overfitting and improve the recognition accuracy. The experimental recognition results for typical plant diseases and pests show that the proposed EResNet‐SVM model has 99.30% test accuracy for eight conditions (seven plant diseases and one normal), which is 5.90% higher than the original ResNet18. Compared with the classic AlexNet, GoogLeNet, Xception, SqueezeNet and DenseNet201 models, the accuracy of the EResNet‐SVM model has improved by 5.10%, 7%, 8.10%, 6.20% and 1.90%, respectively. The testing accuracy of the EResNet‐SVM model for 6 insect pests is 100%, which is 3.90% higher than that of the original ResNet18 model.CONCLUSIONThis research can provide useful references for alleviating the overfitting problem in deep learning, and it can also provide a theoretical and technical support for the intelligent detection and control of plant diseases and pests.This article is protected by copyright. All rights reserved.

show abstract

Analyzing fusion of regularization techniques in the deep learning‐based intrusion detection system

Cited by 21 publications

References 75 publications

New Denial of Service Attacks Detection Approach Using Hybridized Deep Neural Networks and Balanced Datasets

New Denial of Service Attacks Detection Approach Using Hybridized Deep Neural Networks and Balanced Datasets

IMIDS: An Intelligent Intrusion Detection System against Cyber Threats in IoT

EResNet‐SVM: an overfitting‐relieved deep learning model for recognition of plant diseases and pests

Contact Info

Product

Resources

About