A Cloud Intrusion Detection Systems Based on DNN Using Backpropagation and PSO on the CSE-CIC-IDS2018 Dataset

Alzughaibi, Saud; Khediri, Salim El

doi:10.3390/app13042276

Cited by 23 publications

(14 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the FTP-BruteForce attack, HXGBLSTM achieved an accuracy of 100 higher in multi-class classification than that reported in the other literature. Regarding the SSH-Bruteforce attack, our accuracy was 99.97 higher, respectively, than the other algorithms of [26], [8], BWO-CONV-LSTM [27], and [6]. For DDoS-HOIC and Bot attacks, Our accuracy was 99.89 and 99.7 respectively, greater than that of BWO-CONV-LSTM [27].…”

Section: Hxgblstm Vs Other Algorithmsmentioning

confidence: 76%

“…ISCX-IDS 2012, DDoS (Kaggle), CICIDS2017, and CICIDS2018 are four publicly accessible IDS datasets that are used to assess the proposed system. The system achieved a detection accuracy range of 99.79% to 100%, Alzughaibi et al [6] proposed two Deep Neural Network (DNN) models for the CSE-CIC -IDS2018 dataset: one based on a Multi-Layer Perceptron (MLP) with BackPropagation (BP), the other on an MLP with Particle Swarm Optimization (PSO). They obtained results of 98.41% for multi-class classification and 98.97% for binary classification.…”

Section: Literature Reviewmentioning

confidence: 99%

“…The cell memory state is denoted as M (t) and its value at time instance t is expressed in Equation (6).…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

“…To accurately evaluate the effectiveness of HXG-BLSTM, we conducted in-depth comparison with the most recent DL algorithms that were employed in the cyber threat detection literature. In this comparison, we used deep learning algorithms from earlier studies such as [11], [28], [10], [32], [1], [9], BWO-CONV-LSTM [27], [48], [45], [6], [18], [21], [42], and [1]. The results of the comparison for deep learning approaches are shown in Table 9.…”

Section: Hxgblstm Vs Other Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection

Amin,

El-Taweel,

Ali

et al. 2023

mendel

View full text Add to dashboard Cite

The vast amounts of data, lack of scalability, and low detection rates of traditional intrusion detection technologies make it impossible to keep up with evolving and increasingly sophisticated cyber threats. Therefore, there is an urgent need to detect and stop cyber threats early. Deep Learning has greatly improved intrusion detection due to its ability to self-learn and extract highly accurate features. In this paper, a Hybrid XG Boosted and Long Short-Term Memory algorithm (HXGBLSTM) is proposed. A comparative analysis is conducted between the computational performance of six established evolutionary computation algorithms and the recently developed bio-inspired metaheuristic algorithm called Zebra Optimisation Algorithm. These algorithms include the Particle Swarm Optimisation Algorithm, the Bio-inspired Algorithms, Bat Optimisation Algorithm, Firefly Optimisation Algorithm, and Monarch Butterfly Optimisation Algorithm, as well as the Genetic Algorithm as an Evolutionary Algorithm. The dimensionality curse has been mitigated by using these metaheuristic methods for feature selection, and the results are compared with the wrapper-based feature selection XGBoost algorithm. The proposed algorithm uses the CSE-CIC -IDS2018 dataset, which contains the latest network attacks. XGBoost outperformed the other FS algorithms and was used as the feature selection algorithm. In evaluating the effectiveness of the newly proposed HXGBLSTM, binary and multi-class classifications are considered. When comparing the performance of the proposed HXGBLSTM for cyber threat detection, it outperforms seven innovative deep learning algorithms for binary classification and four of them for multi-class classification. Other evaluation criteria such as recall, F1 score, and precision have been also used for comparison. The results showed that the best accuracy for binary classification is 99.8\%, with F1-score of 99.83\%, precision of 99.85\%, and recall of 99.82\%, in extensive and detailed experiments conducted on a real dataset. The best accuracy, F1-score, precision, and recall for multi-class classification were all around 100\%, which does give the proposed algorithm an advantage over the compared ones.

show abstract

Section: Hxgblstm Vs Other Algorithmsmentioning

confidence: 76%

Section: Literature Reviewmentioning

confidence: 99%

“…The cell memory state is denoted as M (t) and its value at time instance t is expressed in Equation (6).…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

Section: Hxgblstm Vs Other Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection

Amin,

El-Taweel,

Ali

et al. 2023

mendel

View full text Add to dashboard Cite

show abstract

“…As illustrated in the pivotal Fig. 1 [3], these categories are: the meticulous signature-based, the analytical statistical anomaly-based, and the hybridized combination techniques.…”

Section: Introductionmentioning

confidence: 99%

From Bytes to Insights: A Systematic Literature Review on Unraveling IDS Datasets for Enhanced Cybersecurity Understanding

Khanan,

Abdelgadir Mohamed,

Mohamed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In the wake of the expanding digital realm, the imperative for robust cybersecurity measures has burgeoned significantly. This extensive investigation digs into the complicated realm of cybersecurity datasets, with the goal of improving our understanding and implementation of these critical tools. This study's comprehensive evaluation of 37 distinct datasets shows a complicated world in which no one dataset stands out as totally suitable for all uses. A precise balance must be struck between crucial dataset qualities such as diversity, authenticity, and usefulness. Using a complete assessment technique, this paper illuminates the challenges and possibilities that developers and researchers face in the field of cybersecurity datasets. Although some databases accurately identify certain forms of cyberattacks, their coverage may not include the whole range of cyber threats. On the other hand, datasets with a strong emphasis on accurate portrayal may forgo comprehensiveness or practical use. This intricacy is heightened by the dynamic and sophisticated nature of cyber threats, emphasizing the delicate balance required between accuracy and practicality. The study emphasizes the necessity of selecting datasets strategically and contextually for cybersecurity studies, with the goal of matching research objectives with the most appropriate dataset selections. Furthermore, it emphasizes the need of continual cooperation and innovation within the cybersecurity community in developing datasets that accurately represent the ever-changing nature of cyber threats. After analyzing 37 cybersecurity datasets, it is obvious that no one dataset can meet all of the field's unique demands, demonstrating the need of a flexible, adaptable, and developing dataset for intrusion detection systems (IDS). This inquiry offers a critical assessment of dataset characteristics and their related issues, providing essential insights for academics, professionals, and dataset creators, enabling the construction of a more resilient and adaptable cybersecurity infrastructure.

show abstract

Ensemble random forest and deep convolutional neural networks in detecting and classifying the multiple intrusions from near real‐time cloud datasets

Khan,

Haroon

2024

Security and Privacy

View full text Add to dashboard Cite

Due to rapidly growing Internet facilities, intruders can steal and misuse the data saved and stored digitally. In this case, securing digital data is challenging but prominent for various purposes. However, the traditional techniques are insufficient to secure these computer networks and cloud information with a 100% success rate. Recently, machine‐ or deep‐learning‐enabled methods have been used to secure network information, but with some limits. Therefore, the study emphasizes detecting and classifying network intrusion using the proposed ensemble and deep learning models. In this case, we developed the ensemble learning‐enabled random forest algorithm and deep learning‐enabled deep convolutional neural network (CNN) models for securing near real‐time cloud information and designed the intrusion detection system accordingly. The complex and high‐volume CSE‐CICIDS2018 datasets were used to test the developed model in Python programming language implemented with several Python libraries. The outcome of the proposed models indicates that the developed models are promising in securing the cloud information with 97.73% and 99.91% accuracies via ensemble‐random forest and deep CNN models. Thus, the present study models can be applied to other real‐time datasets and computer networks to detect cyber threats effectively.

show abstract

A Cloud Intrusion Detection Systems Based on DNN Using Backpropagation and PSO on the CSE-CIC-IDS2018 Dataset

Cited by 23 publications

References 30 publications

A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection

A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection

From Bytes to Insights: A Systematic Literature Review on Unraveling IDS Datasets for Enhanced Cybersecurity Understanding

Ensemble random forest and deep convolutional neural networks in detecting and classifying the multiple intrusions from near real‐time cloud datasets

Contact Info

Product

Resources

About