DeepSeq: learning browsing log data based personalized security vulnerabilities and counter intelligent measures

Abstract

Personalization security is a concern with the rising ability to monitor and access public and personal data by organizations, mainly with gradual integration of human life with their devices. In this paper we have shown how simple browsing log data can jeopardize the identity and the personal integrity of a person along with analysis of preventive measures to protect them. As people get digitally enslaved, unknowingly browsing logs inherited certain unique behaviors of the people. It can be characterized and used for monitoring them and their aligned social, professional and organizational counterparts. It is quite a challenge for modern systems to keep attackers at bay and prevent them from gathering and analyzing activity data which can be used to identify specific, easy and valuable targets. Our analysis is based on modeling efficient systems for justification of the possible vulnerabilities and counter-measures through data driven approaches to learn and analyze such data and derive the extent these data can be exploited. Overall, we achieved an accuracy of 85% for identification of targeted characteristics using log data features using deep learning models, which achieved better than other learning models, thus effectively pointing out to the fact that there is severe non-linearity and combination possibilities in the data.