A novel approach for phishing URLs detection using lexical based machine learning in a real-time environment

Gupta, Brij B.; Yadav, Kuldeep; Razzak, Imran; Psannis, Kostas E.; Castiglione, Arcangelo; Chang, Xiaojun

doi:10.1016/j.comcom.2021.04.023

Cited by 93 publications

(23 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For many decades, malicious URL detection has been a major concern for cybersecurity specialists [8][9][10][11][12][13][14]. Several solutions have been proposed to detect malicious URLs and protect users from being victims of an attack.…”

Section: Related Workmentioning

confidence: 99%

“…To evaluate the proposed model, the commonly used machine learning techniques that were used to evaluate the related malicious URL detection were used. Moreover, three models were developed for the evaluation of the CTI-MURLD, Google-CTI, Whois-CTI, and lexical URL-based features as baselines [8,11,[13][14][15]23,41]. Furthermore, two deep learning-based models were developed for the evaluation of SDL and CNN-based malicious URL-detection models.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…The problem with detecting malicious websites has been around since early 2004 [8][9][10][11][12][13][14][15][16][17][18]. Many solutions have been proposed to accurately detect these websites.…”

Section: Introductionmentioning

confidence: 99%

“…Many solutions have been proposed to accurately detect these websites. These solutions can be divided into three categories by their source of investigation: URL-based [8][9][10][11][12][13][14][15][16], web content-based [19][20][21], and script-based [17,18]. URL-based detection is the most investigated approach followed by content-based detection, while little research has been investigated on script-based detection.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Cyber Threat Intelligence-Based Malicious URL Detection Model Using Ensemble Learning

Ghaleb

Alsaedi

Saeed

et al. 2022

Sensors

View full text Add to dashboard Cite

Web applications have become ubiquitous for many business sectors due to their platform independence and low operation cost. Billions of users are visiting these applications to accomplish their daily tasks. However, many of these applications are either vulnerable to web defacement attacks or created and managed by hackers such as fraudulent and phishing websites. Detecting malicious websites is essential to prevent the spreading of malware and protect end-users from being victims. However, most existing solutions rely on extracting features from the website’s content which can be harmful to the detection machines themselves and subject to obfuscations. Detecting malicious Uniform Resource Locators (URLs) is safer and more efficient than content analysis. However, the detection of malicious URLs is still not well addressed due to insufficient features and inaccurate classification. This study aims at improving the detection accuracy of malicious URL detection by designing and developing a cyber threat intelligence-based malicious URL detection model using two-stage ensemble learning. The cyber threat intelligence-based features are extracted from web searches to improve detection accuracy. Cybersecurity analysts and users reports around the globe can provide important information regarding malicious websites. Therefore, cyber threat intelligence-based (CTI) features extracted from Google searches and Whois websites are used to improve detection performance. The study also proposed a two-stage ensemble learning model that combines the random forest (RF) algorithm for preclassification with multilayer perceptron (MLP) for final decision making. The trained MLP classifier has replaced the majority voting scheme of the three trained random forest classifiers for decision making. The probabilistic output of the weak classifiers of the random forest was aggregated and used as input for the MLP classifier for adequate classification. Results show that the extracted CTI-based features with the two-stage classification outperform other studies’ detection models. The proposed CTI-based detection model achieved a 7.8% accuracy improvement and 6.7% reduction in false-positive rates compared with the traditional URL-based model.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cyber Threat Intelligence-Based Malicious URL Detection Model Using Ensemble Learning

Ghaleb

Alsaedi

Saeed

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Data Understanding. All kinds of data used in sports prediction can be obtained from online public channels in most cases [21]. Part of the research work completed in the early stage can automatically collect motion data.…”

Section: Solutions To Research Problemsmentioning

confidence: 99%

Sports Performance Prediction Based on Chaos Theory and Machine Learning

Sun

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In order to combine chaos theory and machine learning technology to predict sports performance, a research on sports performance prediction based on chaos theory and machine learning is proposed. This paper takes the sports performance as the goal to predict the data; introduce the chaos theory algorithm, and combine the neural network system and particle swarm optimization algorithm to actively train sports results and ensure the quality of performance prediction. The comparison between shot put data prediction and real data shows that the prediction results given by the model have little deviation and can provide technical services for performance prediction for special sports training. When predicting the sports performance of college students, the prediction accuracy of sports performance of each subject is no less than 90%, which proves that this system can be used in college sports management. The delay time of the model data is short, which is mainly related to the correlation coefficient. When the coefficient is determined to be 0.02, the prediction delay time is 5 s, which can effectively complete the prediction and analysis of sports performance. The combined model has various technical advantages such as chaos theory, neural system, and particle optimization. It has strong sports performance prediction ability and can provide technical support for performance prediction for athletes’ training, college sports management, and other related sports industries.

show abstract

A content and URL analysis‐based efficient approach to detect smishing SMS in intelligent systems

Jain

Gupta

Kaur

et al. 2022

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

Smishing is a combined form of short message service (SMS) and phishing in which a malicious text message or SMS is sent to mobile users. This form of attack has come to be a severe cyber‐security difficulty and has triggered incredible monetary losses to the victims. Many antismishing solutions for mobile devices have been proposed till date but still, there is a lack of a full‐fledged solution. Therefore, this paper proposes an efficient approach that analyzes text content and uniform resource locator (URL) presented in the SMS. We have integrated the URL phishing classifier with the text classifier to improve accuracy as some of the SMS contain the URL with no text or much less text. To find out rare words in a report, depending upon the frequency of term (TF) and the reciprocal of document frequency TF‐inverse document frequency (IDF), a weighting framework TF‐IDF is used. We have used two data sets for both text as well as for URL phishing classifier and used a synthetic minority oversampling technique to balance the training data. The voting classifier simply merges the findings of each classifier passed into it and predicts the output on the basis of voting. In proposed approach integrating KNN, RF, and ETC can detect smishing messages with a 99.03% accuracy and 98.94% precision rate which is relatively efficient compared with existing ones like SmiDCA model which has the given accuracy of 96.40% using Random Forest classifier in BFSA, Feature‐Based it has an accuracy of 98.74% and 94.20% true positive rate and Smishing Detector it shows an overall accuracy of 96.29%.

show abstract

A novel approach for phishing URLs detection using lexical based machine learning in a real-time environment

Cited by 93 publications

References 20 publications

Cyber Threat Intelligence-Based Malicious URL Detection Model Using Ensemble Learning

Cyber Threat Intelligence-Based Malicious URL Detection Model Using Ensemble Learning

Sports Performance Prediction Based on Chaos Theory and Machine Learning

A content and URL analysis‐based efficient approach to detect smishing SMS in intelligent systems

Contact Info

Product

Resources

About