A Paradigm for DoS Attack Disclosure using Machine Learning Techniques

Abualhaj, Mosleh M.; Abu-Shareha, Ahmad Adel; Hiari, Mohammad O.; Alrabanah, Yousef; Al-Zyoud, Mahran; Alsharaiah, Mohammad A.

doi:10.14569/ijacsa.2022.0130325

Cited by 8 publications

(18 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It gives each category in the variable a special numerical value. When the category variable has an intrinsic order or ranking, this encoding is often utilized [10]. Regarding the MalMem-2022 that is being utilized, the output field is textual and contains 4 values of main categories and 16 values of sub categories [18].…”

Section: Transformationmentioning

confidence: 99%

“…The popular data normalizing method known as "min-max scaling" is used in ML to scale numerical features to a particular range, usually between 0 and 1. It maintains the relative ordering of the data points while linearly transforming the original values to a normalized scale [10]. The min-max scaling formula (1).…”

Section: Normalizationmentioning

confidence: 99%

“…These cutting-edge malware techniques demonstrate how constantly changing cyber risks are and how urgent it is for businesses to use cutting-edge security measures that go beyond typical anti-malware solutions [8], [9]. Machine learning (ML) approaches can be used to protect against malware by improving the detection and prevention capabilities of security systems [9], [10]. The goal of ML is to create methods and models that let computers learn and make predictions or judgments without having to be explicitly programmed.…”

Section: Introductionmentioning

confidence: 99%

“…Malware detection, behavioral analysis, dynamic analysis, and feature extraction are just a few of the numerous ways that ML can be used in the context of malware. ML methods can be broadly divided into three categories: reinforcement learning, unsupervised learning, and supervised learning (SL) [9], [10].…”

Section: Introductionmentioning

confidence: 99%

“…Because it can identify patterns and traits of malware from labeled data, SL is a widely utilized approach in malware detection. The labeled dataset's quality, the feature selection, and the choice of the best methods all affect how well malware may be detected using SL [10]- [12]. The data's type, the virus's complexity, and the required trade-offs between accuracy, performance, and interpretability all play a role in choosing the best methods for malware detection.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Tuning the k value in k-nearest neighbors for malware detection

Abualhaj,

Abu-Shareha,

Shambour

et al. 2024

IJ-AI

View full text Add to dashboard Cite

<span>Malicious software, also referred to as malware, poses a serious threat to computer networks, user privacy, and user systems. Effective cybersecurity depends on the correct detection and classification of malware. In order to improve its effectiveness, the K-Nearest Neighbors (KNN) method is applied systematically in this study to the task of malware detection. The study investigates the effect of the number of neighbors (K) parameter on the KNN's performance. MalMem-2022 malware datasets and relevant evaluation criteria like accuracy, precision, recall, and F1-score will be used to assess the efficacy of the suggested technique. The experiments evaluate how parameter tuning affects the accuracy of malware detection by comparing the performance of various parameter setups. The study findings show that careful parameter adjustment considerably boosts the KNN method's malware detection capability. The research also highlights the potential of KNN with parameter adjustment as a useful tool for malware detection in real-world circumstances, allowing for prompt and precise identification of malware.</span>

show abstract

Section: Transformationmentioning

confidence: 99%

Section: Normalizationmentioning

confidence: 99%