Journal of Systems and Software
| Hi-index | 0.00 |
Cloud security is a major concern that may delay its widespread adoption. User access control (UAC) is the core component of security in cloud computing environment, aiming to ensure that stored data are allowed to be accessed only by authenticated/authorized users. As a typical behavioural biometrics, keystroke dynamics provides a promising UAC solution. The most challenging issue that hinders the wide deployment of keystroke is the high verification error rate. Gunetti et al. proposed a classical n-graph-based keystroke verification method (GP method), which can achieve a low False Acceptance Rate (FAR). However, the GP method suffers from a high False Rejection Rate (FRR) and a severe scalability issue. Thus, GP is not a feasible solution for computing cloud application where scalability is a big issue. In this paper, two keystroke verification approaches (nGdv-V and nGdv-C) are proposed to overcome GP's shortcomings. To reduce high FRR, we designed a new correlation measure using n-graph equivalent feature (nGdv) that enables more accurate recognition for genuine users. Moreover, correlation-based hierarchical clustering is proposed to address the scalability issue. The experimental results show that the nGdv-C can produce much lower FRR while achieving almost the same level of FAR as that of the GP method. Furthermore, 1250 times (when using nGdv-V) and three times (when using nGdv-C(17,4)) authentication speed gains have been achieved.