Detection of E-Mail Phishing Attacks – using Machine Learning and Deep Learning

Phishing is the most prominent cyber-crime that uses camouflaged e-mail as a weapon. In simple words, it is defined as the strategy adopted by fraudsters in-order-to get private details from persons by professing to be from wellknown channels like offices, bank, or a government organization. In this era of modernization, electronic mails are accustomed globally as communiqu channel for both private and professional purposes. The particulars exchanged over emails are often confidential and sensitive for example info of bank statements, payment bills, debit-credit reports, and authentication data. This makes e-mails precious for hackers because they can exploit these details for maleficent intends. The main goal of the attackers is to acquire personal details by deceiving the e-mail recipient to click noxious link or download the attachment under false pretences. In the last few years, there is an exponential rise in cyber threats including the major ones, phishing e-mails have result in huge monetary and identity losses. Several models have been developed to separate ham and phished e-mails but attackers are always trying new methods to invade the privacy of the people. Hence, there is dire need to perpetually develop new models or to upgrade the existing ones. The focus of the paper is to elaborate that specifically centers around on both machinelearning (ML) and deep-learning (DL) approaches for detecting phishing e-mails. It shows comparative analysis and assessment of various DL and ML models that were proposed in the last few decades to classify phishing e-mails at different stages of crime in a systematic manner. This paper discusses the problem's concept, its explication, and the anticipated future directions.