A Study of AIOT in Detecting Social Engineering Attacks: Phishing and Identity Theft

Abstract

With the advancement of technology, the Internet is becoming ubiquitous and available to everybody. There is a plethora of websites that provide various advantages. Despite their large quantity, not all these websites are genuine. Phishing sites are websites that trick people into serving their objectives. Phishing assaults, which have been around for ages and are still a huge issue today, pose a severe threat to the cyber world. Attackers are using a variety of innovative and inventive tactics to carry out phishing assaults, which are on the rise. Web browsing’s pervasiveness in our everyday lives, however, is not without security hazards. This standard web browsing habit, along with web users’ poor situational awareness of cyber dangers, exposes them to Phishing, malware, and profiling, among other hazards. Furthermore, phishing assaults are frequently used as an attack vector or the first stage in a more complex attack in today’s security climate. The usual method of comparing websites by using a blacklist and a whitelist is ineffective. As attackers have gotten more sophisticated in concealing and redirecting URLs, they may now fool users into phishing attacks without being caught. These Phishing attacks are used to commit all sorts of criminal activities like identity theft, whether in the form of Document theft, financial fraud, or medical fraud.   As   a   result,   new   methodologies on machine learning algorithms (ML) are required to detect these phishing websites.