Abstract:

The popularity of mobile devices is increasing day by day as they provide a large variety of services by reducing the cost of services. Short Message Service (SMS) is considered one of the widely used communication service. However, this has led to an increase in mobile devices attacks like SMS Spam. In this paper, we present a novel approach that can detect and filter the
spam messages using machine learning classification algorithms. We study the characteristics of spam messages in depth and then found ten features, which can efficiently filter SMS spam messages from ham messages. MultonomialNavybayes, decision tree classifier,linearSVC,Xgboost ,Logistic Regression.
Keywords: SMS spam ,Mobile devices ,Machine learning _ Feature selection

Introduction:

Short Message Service (SMS) is one of the popular communication services in which a message is sent electronically. The reduction in the cost of SMS services by telecom companies has led to the increased use of SMS. This rise attracted attackers which have resulted in SMS Spam problem. A spam message is generally any unwanted message that is sent to user’s mobile phone. Spam messages include advertisements, free services, promotions, awards, etc. People are using SMS messages to communicate rather than emails because while sending SMS message there is no need of internet connection and it is simple and efficient . The SMS Spam problem is increasing day by day with the increase in the use of text messaging. There are various security measures available to control SMS Spam problem but they are not so mature. Many android apps are also on play store to block spam messages but people are not aware of these apps due to lack of knowledge. Other than apps the filtering techniques available mainly focuses on email spam as email spam is one of the oldest problem but with the popularity of mobile devices,
SMS spam is the one of the major issue these days. SMS is one of the cheapest ways to communicate and can be considered as the simplest way to perform phishing attacks as mobile devices contain sensitive and personal information like card details, username, password, etc. Attackers are finding different ways to steal this information from mobile devices.

Problem statement:

SMS is one of the cheapest ways to communicate and can be considered as the simplest way to perform phishing attacks as mobile devices contain sensitive and personal information like card details, username, password.

Objective:

Ihe main aim of the project it can detect and filter the spam messages using machine learning classification algorithms. We have used a feature set of features for classification. These features can differentiate a spam SMS from ham SMS. Machine learning techniques were effective in email spam filtering as it helps in preventing zero-day attacks and provides the high level of security.