Despite being the most widely used authentication mechanism, password-based authentication is not very secure, being easily guessed or brute-forced. To address this, many systems which especially value security adopt Multi-Factor Authentication (MFA), in which multiple different authentication mechanisms are used concurrently. JitHDA (Just-in-time human dynamics based authentication engine) is a new authentication mechanism which can add another option to MFA capabilities. JitHDA observes human behaviour and human dynamics to gather up to date information on the user from which authentication questions can be dynamically generated. This paper proposes a system that implements JitHDA, which we call Autonomous Inquiry-based Authentication Chatbot (AIAC). AIAC uses anomalous events gathered from a user’s recent activity to create personalized questions for the user to answer, and is designed to improve its own capabilities over time using neural networks trained on data gathered during authentication sessions. Due to using the user’s recent activity, they will be easy for the authentic user to answer and hard for a fraudulent user to guess, and as the user’s recent history updates between authentication sessions new questions will be dynamically generated to replace old ones. We intend to show in this paper that AIAC is a viable implementation of JitHDA.
The rising importance of Big Data in modern information analysis is supported by vast quantities of user data, but it is only possible to collect sufficient data for all tasks within certain data-gathering contexts. There are many cases where a domain is too novel, too niche, or too sparsely collected to adequately support Big Data tasks. To remedy this, we have created ADG Engine that allows for the generation of additional data that follows the trends and patterns of the data that’s already been collected. Using a database structure that tracks users across different activity types, ADG Engine can use all available information to maximize the authenticity of the generated data. Our efforts are particularly geared towards data analytics by identifying abnormalities in the data and allowing the user to generate normal and abnormal data at custom ratios. In situations where it would be impractical or impossible to expand the available dataset by collecting more data, it can still be possible to move forward with algorithmically expanded data datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.