Iterative Feature Selection-Based DDoS attack Prevention Approach in Cloud

Naiem, Sarah; Khedr, Ayman E.; Idrees, Amira M.; Marie, M.M.

doi:10.32985/ijeces.14.2.9

Cited by 4 publications

(7 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This may be due to the level of independence of the features or the probabilistic nature of the classifier. In [29], an iterative feature selection approach was proposed using the CICDDoS2018 dataset where the authors applied four different feature selection approaches, including Pearson Correlation Coefficient PCC, RFFI, MI, and Chi-square and created four different sets of features, selected the set of features with the highest independence which was the PCC set of features and then used the other three techniques to select a subset of features for each technique resulting in 3 more subsets. After that, they tested them using DT, RF, and GNB.…”

Section: [23]mentioning

confidence: 99%

“…Our proposed framework aims to improve the accuracy of the GNB, where we are handling the zero-probability problem through the data pre-processing phase. Moreover, we considered selecting the set of features with the highest level of independence by applying the iterative feature selection approach we proposed in [29]. Each stage of our framework is described in detail in the following sections.…”

Section: Proposed Frameworkmentioning

confidence: 99%

“…This method encompasses the benefits of both the wrapper and filter methods and maintains reasonable computational costs examples include Random Forest Feature Importance (RFFI) and LASSO Regularization (L1) [41] [42] [24] [26]. As stated in the literature review section, authors in [21] [22] [24] [29] highlighted that the use of more than one approach results in better accuracy and reliable classification. As mentioned in our previous research [29] we used the same iterative approach.…”

Section: Feature Selectionmentioning

confidence: 99%

“…This type of attack is very challenging to detect, resulting from its distributed nature. It is the idea of creating several bots or zombies and sending them as many requests as possible to the machine, resulting in system failure by preventing others from using the system [5]. According to the latest statistics and research, "Cisco's analysis of DDoS total attack history and predictions," the total number of DDOS attacks has increased from 7.9 million in 2018 to 15.4 million in 2023.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Enhancing the Efficiency of Gaussian Naïve Bayes Machine Learning Classifier in the Detection of DDOS in Cloud Computing

Naiem,

Khedr,

Idrees

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Distributed Denial of services is one of the most dangerously planned attacks in cloud computing, resulting in huge losses of data and money for both the cloud services providers and the users of these services. Many efforts have been performed to help protect the cloud from these attacks using machine learning techniques. This study focuses on enhancing the efficiency of the Gaussian Naïve Bayes classifier, considered one of the cheapest and fastest classifiers. Still, it has some problems resulting from its equation's statistical nature. The nature of this classifier is based on multiplication, resulting in inaccurate classification due to the zero-frequency issue and the fact that it assumes that features are independent. This research proposed a framework handling the selection of a set of highly independent features following an iterative feature selection approach using the Pearson Correlation Coefficient, Mutual Information, and Chi-squared and then selecting other subsets of features from these sets to reach a set of highly independent features. After that, we used a specific algorithm handling the data pre-processing to handle the zero-frequency problem where we used the Mode to replace the missing values, and if the mode was zero, it used the mean instead. Still, if the record's label is zero, we get the value of the previous record with zero labels. After that, we handled the data imbalances using SMOTE. These enhancements increased both accuracy for the mutual information model by 2% and the average overall accuracy and precision by 1.5%.

show abstract

Section: [23]mentioning

confidence: 99%

Section: Proposed Frameworkmentioning

confidence: 99%

Section: Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing the Efficiency of Gaussian Naïve Bayes Machine Learning Classifier in the Detection of DDOS in Cloud Computing

Naiem,

Khedr,

Idrees

et al. 2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Quality is the force needed to effectively drive the university education system to achieve its goals and mission by the community and interested parties in university education [11]. Recent trends in quality measurement and management enhance the directional, cognitive, professional, and behavioral characteristics of graduates, as well as the quality of the elements of the educational service delivery system [12].…”

Section: Introductionmentioning

confidence: 99%

The Impact of Applying ISO Standards Systems on Improving the Quality of the Performance in Higher Educational Institutions in Egypt

Mounir

Idrees

Khater

et al. 2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Applying ISO 21001:2018 standard ensures that universities have a competitive advantage as well as the achievement of their objectives. This study aims to identify the impact of implementing ISO 21001: 2018 management systems standards on the performance quality of higher education institutions. The study investigates the reasons why private higher education institutions seek ISO standards certificates in general and the specifications of management systems for educational institutions in particular. The study applied a set of statistical testing methods on paired samples as well as independent samples to ensure quality assurance. The study also proposes the required prerequisites that should be considered. The study investigated a hypothesis stating that "there are no statistically significant differences before and after applying the ISO 21001:2018 management systems specification for educational institutions in improving the quality of performance in higher education institutions" which was rejected by conducting an experiment in Future University in Egypt and accepting the alternative hypothesis. The study confirmed the impact of quality which was previously investigated by prior research that has been discussed in this study. The study further presented the need to apply quality based on determined criteria which were not considered in prior studies. Moreover, the study proposed the impact of ISO standards in educational institutions in general and in Egypt in specific. This recommendation is proved by this study to enhance the quality level in educational institutions.

show abstract

Elevating Driver Behavior Understanding With RKnD: A Novel Probabilistic Feature Engineering Approach

Shariful Islam,

Abu Tareq Rony,

Safran

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Early detection of driver behavior is a pivotal aspect in enhancing road safety, focusing on identifying and mitigating risky driving patterns before they lead to accidents. The use of smartphone sensors for data acquisition marks a significant advancement in this field. It allows for continuous, real-time monitoring of driving patterns without the need for specialized equipment. In this study, we leverage a publicly available smartphone motion sensor dataset, utilizing accelerometer and gyroscope data from a Samsung Galaxy S21 to analyze driving behaviors classified as slow, normal, and aggressive. This research introduces a novel feature engineering technique named the RKnD (Random forest, K-nearest classifier, Decision tree) probabilistic feature engineering technique, which integrates three prominent machine learning (ML) models. This blend offers a robust analysis of driver behavior, leveraging the strengths of each algorithm. This paper emphasizes the importance of data balancing in machine learning, employing the Synthetic Minority Oversampling Technique (SMOTE) to enhance the reliability of the predictions. Furthermore, k-fold crossvalidation is used to ensure the model's consistency and accuracy across original features and the proposed RKnD probabilistic features of the data sets. By achieving such high accuracy, the study demonstrates the potential of smartphone-based systems to significantly improve road safety. This paper introduces a novel approach utilizing smartphone motion sensor data to detect driver behaviors with a remarkable accuracy rate of 99.63%. This research stands out for its application of machine learning techniques in a practical, accessible manner. This pioneering approach named RKnD feature engineering sets a new standard in the realm of smart transportation systems, opening avenues for further innovations in the field, and filling a gap in road safety analysis to avoid road accidents. Future research on RKnD should streamline its algorithm for real-time use, diversify datasets, integrate advanced Deep Learning for complex pattern detection, and undertake real-world testing to validate practicality and uncover challenges.

show abstract

Iterative Feature Selection-Based DDoS attack Prevention Approach in Cloud

Cited by 4 publications

References 15 publications

Enhancing the Efficiency of Gaussian Naïve Bayes Machine Learning Classifier in the Detection of DDOS in Cloud Computing

Enhancing the Efficiency of Gaussian Naïve Bayes Machine Learning Classifier in the Detection of DDOS in Cloud Computing

The Impact of Applying ISO Standards Systems on Improving the Quality of the Performance in Higher Educational Institutions in Egypt

Elevating Driver Behavior Understanding With RKnD: A Novel Probabilistic Feature Engineering Approach

Contact Info

Product

Resources

About