Phishing detection system using nachine learning classifiers

Zaini, Nur Sholihah; Stiawan, Deris; Razak, Mohd Faizal Ab; Firdaus, Ahmad; Din, Wan Isni Sofiah Wan; Kasim, Shahreen; Sutikno, Tole

doi:10.11591/ijeecs.v17.i3.pp1165-1171

Cited by 16 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, obtaining good results depends on the techniques used, and the way in which we create our models. Generally speaking, improving the results of ML models can be done in several ways, for example by adjusting the model's hyperparameters as proposed in this article or by selecting the most relevant features [62]- [68]. On the other hand, this selection is in the framework of traditional models [69]- [74], this concept is still not valid, when it comes to DL models [75]- [80], if the model needs optimisation, in this case other methods must be sought, as the selection of the most relevant features is done automatically in most cases [81].…”

Section: Resultsmentioning

confidence: 99%

Machine learning-based intrusion detection system for detecting web attacks

Abdou Vadhil,

Lemine Salihi,

Farouk Nanne

2024

IJ-AI

View full text Add to dashboard Cite

The increasing use of smart devices results in a huge amount of data, which raises concerns about personal data, including health data and financial data. This data circulates on the network and can encounter network traffic at any time. This traffic can either be normal traffic or an intrusion created by hackers with the aim of injecting abnormal traffic into the network. Firewalls and traditional intrusion detection systems detect attacks based on signature patterns. However, this is not sufficient to detect advanced or unknown attacks. To detect different types of unknown attacks, the use of intelligent techniques is essential. In this paper, we analyse some machine learning techniques proposed in recent years. In this study, several classifications were made to detect anomalous behaviour in network traffic. The models were built and evaluated based on the Canadian Institute for Cybersecurity-intrusion detection systems dataset released in 2017 (CIC-IDS-2017), which includes both current and historical attacks. The experiments were conducted using decision tree, random forest, logistic regression, gaussian naïve bayes, adaptive boosting, and their ensemble approach. The models were evaluated using various evaluation metrics such as accuracy, precision, recall, F1-score, false positive rate, receiver operating characteristic curve, and calibration curve.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine learning-based intrusion detection system for detecting web attacks

Abdou Vadhil,

Lemine Salihi,

Farouk Nanne

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Zaini et al [28] investigated the effectiveness of machine learning in the classification of phishing attacks. Their study compared five classifiers to find the best machine learning classifiers in detecting phishing attacks.…”

Section: Literature Reviewmentioning

confidence: 99%

Empirical Evidence of Socially-Engineered Attack Menace Among Undergraduate Smartphone Users in Selected Universities in Nigeria

2021

IJATCSE

View full text Add to dashboard Cite

Smartphone proliferation today, have up-scaled user adoption of Internet-based processing activities. These include (not limited to) e-learning, e-commerce, mobile-banking and others –all aimed at better performance, service delivery at improved execution speed, greater portability, flexibility and accessibility ease. Thus, necessitating growth expansion in mobile-app development across varying platforms that are poised to help users accomplish processing tasks while harnessing the benefits of the technology. Conversely, these techs have also allowed users to be constantly besieged by threats and security breaches. In lieu of residence, sensitive and proprietary –users have become bothered with smartphone exposure to possible data loss and theft –if they are to further adopt these new paradigms. With doubt in their minds, trust levels in user adoption continues to reduce. We seek to investigate social-engineered threats and attacks amongst undergraduates in Nigerian Universities. Result shows that phishing hits a higher successrate against smartphone users in Nigeria, which has decreased client’s trust level in Internet-based services

show abstract

“…A feature descriptor or the combination of feature descriptors will result in the best classification process to determine the condition of the transformer oil. Three classification models [20] are used to measure the performance of classifier to classify the pre-and breakdown condition.…”

Section: Figure 1 Example Of Electric Field Bridging Formation In Rgmentioning

confidence: 99%

Electric field bridging pattern of pre-breakdown and breakdown condition in transformer oil

Mustafa

Ali

Zainuddin

et al. 2020

IJEECS

View full text Add to dashboard Cite

Transformer is considered as one of the most important equipment in electrical power system networks. However, most problems occurred in transformer were related to the defects and weakness of the insulation systems. The oils used in transformer act as coolant and insulation purposes hence maintaining the dielectric strength of the transformer. In this work, electric field bridging pattern is observed from pre-breakdown and breakdown condition. The electric field bridging formation was recorded in the experimental setup and images were captured per frame. 193 images were randomly chosen from the whole video frames where 102 images were the pre-breakdown images and 91 images were the breakdown images. This system comprises of four stages: (i) a preprocessing stage to mark the electrodes tips and background subtraction; (ii) a segmentation stage to extract the electric field bridging formation in region of interest; (iii) a feature extraction stage to extract electric field bridging using feature descriptors, area, minor-axis and major-axis length (iv) a classification stage to identify the pre-breakdown and breakdown condition. System performance was evaluated using support vector machine (SVM), k-nearest neighbour (k-NN) and random forest (RF) and SVM provided the most promising accuracy that was 99%. The results show that the combination of three feature descriptors, area, minor-axis and major-axis length are the best features combination in identifying the transformer oil condition. In future work, further studies will be conducted to investigate the pattern of pre- and post-breakdown due to some similarity found in image pattern. Due to that, more feature descriptors will be identified to find a unique pattern between pre- and post-breakdown condition

show abstract

Phishing detection system using nachine learning classifiers

Cited by 16 publications

References 17 publications

Machine learning-based intrusion detection system for detecting web attacks

Machine learning-based intrusion detection system for detecting web attacks

Empirical Evidence of Socially-Engineered Attack Menace Among Undergraduate Smartphone Users in Selected Universities in Nigeria

Electric field bridging pattern of pre-breakdown and breakdown condition in transformer oil

Contact Info

Product

Resources

About