An adaptive approach towards the selection of multi-factor authentication


Authentication is the fundamental defense against any illegitimate access to a computing device or any sensitive online applications. Due to recent trends of emerging security threats, authentication using only a single factor is not reliable to provide adequate protection for these devices and applications. Hence, to facilitate continuous protection of computing devices and other critical online services from an un-Authorized access, multi-factor authentication emerges as a viable option. Many authentication mechanisms with varying degrees of accuracy and portability are available for different types of computing devices connected with various communicating media. As a consequence, several existing and well-known multi-factor authentication strategies have already been utilized to enhance the security of various applications. Keeping this in mind, this research is focused on designing a robust and scalable framework for authenticating a legitimate user efficiently through a subset of available authentication modalities along with their several features (authentication factors) in time-varying operating environments (devices, media and surrounding conditions) on a regular basis. This paper highlights the creation of a trustworthy framework to quantify different authentication factors in terms of selection of different types of devices and media. In addition, a novel adaptive selection strategy for the available authentication factors incorporating the trustworthy values, previous history of selection as well as surrounding conditions is proposed in the paper. Selection through adaptive strategy ensures the incorporation of the existing environmental conditions within the selection of authentication factors and provides better diversity in the selection of these factors. Simulation results show that the proposed selection approach performs better than other existing selection strategies, namely, random and optimal selections in different settings of operating environments.

Publication Title

Proceedings - 2015 IEEE Symposium Series on Computational Intelligence, SSCI 2015