Improved Biba model based on trusted computing

Abstract Biba model is hard to implement because the rules are too strict to meet the flexibility of system. To enhance the flexibility, the low‐water‐mark policy based on the Biba model is proposed by supporting the dynamic change of subject tags. However, the biggest drawback of low‐water‐mark policy is that the integrity level of the subjects in a system decreases monotonously, which results that some subjects cannot access most of the objects and the system life cycle is cut down. An improved model is proposed based on the Biba model, which not only describes the infection degree of subjects by separating the subject into uninfected and infected subjects and introducing the confidence interval but also reduces the decline rate of integrity level of the subject and prolongs the life time cycle by adopting trusted computing to adjust subject tags. Theory analysis and experiment show that the improved model enhances the availability of system. Copyright © 2015 John Wiley & Sons, Ltd.