Abstract
Measurement and reporting of dynamic behavior of a target application is a pressing issue in the Trusted Computing paradigm. Remote attestation is a part of trusted computing, which allows monitoring and verification of a complete operating system or a specific application by a remote party. Several static remote attestation techniques have been proposed in the past but most of the feasible ones are static in nature. However, such techniques cannot cater to dynamic attacks such as the infamous Heartbleed bug. Dynamic attestation offers a solution to this issue but is impractical due to the infeasibility of measurement and reporting of enormous runtime data. To an extent, it is possible to measure and report the dynamic behavior of a single application but not the complete operating system. The contribution of this paper is to provide the design and implementation of a scalable dynamic remote attestation mechanism that can measure and report multiple applications from different stakeholders simultaneously while ensuring privacy of each stakeholder. We have implemented our reference monitor and tested on Linux Kernel. We show through empirical results that this design is high scalable and feasible for a large number of stakeholders.