Phishing Detection using Machine Learning Techniques
Meenu1, Sunila Godara2
1Meenu, Department of, Computer Science, Guru Jambeshwar University of Science and Technology, hisar, Haryana, India.
2Sunila Godara, Department of, Computer Science, Guru Jambeshwar University of Science and Technology, hisar, Haryana, India.
Manuscript received on November 21, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 3820-3829 | Volume-9 Issue-2, December, 2019. | Retrieval Number: B4095129219/2019©BEIESP | DOI: 10.35940/ijeat.B4095.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Phishing is a type of cyber-crime where spammed messages and false sites allure exploited people to give delicate data to the phishers. The obtained touchy data is along these lines used to take characters or access cash. To battle against spamming, a cloud-based framework Microsoft azure and uses prescient investigation with machine making sense of how to manufacture confidence in personalities. The goal of this paper is to construct a spam channel utilizing various machine learning techniques. Classification is a machine learning strategy uses that can be viably used to recognize spam, builds and tests models, utilizing diverse blends of settings, and compares various machine learning technique, and measure the exactness of a prepared model and figures a lot of assessment measurements. The present study compares the predictive accuracy, f1 score, precession and recall of several machine learning methods including Logistic Regression (LR), Support Vector Machines (SVM), Decision Tree (DT), and Neural Networks (NNet) for predicting phishing emails and improves logistic regression technique by using feature selection methods and improves the accuracy to detect phishing.
Keywords: DT , LR, NN, Phishing, SVM.