Posted Date : 03rd Jun, 2023
Publishing in UGC-approved journals offers several advantages, includi...
Posted Date : 03rd Jun, 2023
UGC-approved journals refer to the scholarly journals that have been a...
Posted Date : 09th Sep, 2022
The University of Pune is going to update the ugc care listed journals...
Posted Date : 09th Sep, 2022
IJARESM Publication have various tie ups with many Conference/Seminar ...
Posted Date : 07th Mar, 2022
Call For Papers : LokSanwad Foundation Aurangabad, Maharashtra One Day...
An Overview of Intrusion Detection in Mobile Phone Using Data Mining Techniques
Author Name : Dauda Abdu, Shiv Kumar
ABSTRACT
Frequently security threats are command against mobile phone as the devices’ computing power as well as storage capabilities in advance. So many Preventive measures such as authentication, encryption alone are not enough to provide efficient security for a system. There is need for another security such as Intrusion detection systems that will improved the security and uses fewer resources on the smart phone. An intrusion detection method is proposed in order to detect intrusions in smart phones using Data Mining techniques. Moreover, network-based approach is tweetable to remove the overhead processing from the mobile phones. In addition neural network classifier will be built and trained for each user based on their call logs. The intrusion detection application that installed and runs on mobile phone of the users and will collects the data or information of the user and sends the data to the remote server. Moreover, the call logs will then fed to the trained classifier, in order to analyze the logs, and sends back the report or feedback via emails or text as quickly as possible to the mobile phones whenever abnormalities are found. In addition, we compared so many different neural classifiers to identify the best classifier with better performance. In addition, the results shows clearly the effectiveness and efficiency of the ways to detect intrusions.
Keywords: Intrusion, Data Mining, Naïve Bayes, SVM, HTML, Firebase, Android