Data Re-Outsourcing Detection With Latency-Constraint for Edge Storage

Edge storage has become a widely used solution for providing low-latency data access services, which motivates data owners to outsource data on geographically distributed edge nodes to deliver a positive user experience. Nevertheless, various security concerns raise in terms of data availability. Among them, edge data geo-location verification becomes a prominent concern when the data is out of owners’ control, since outsourced data may be re-outsourced to other economical yet unknown third-party devices by dishonest edge nodes for saving storage space and pocketing the difference. Existing geo-localization approaches for cloud architectures can not be practically applied to identify such re-outsourcing behaviors due to the uniqueness of edge storage. To close this gap, we make the first attempt to investigate the edge data re-outsourcing detection (EDRD) problem, enabling the data owner to inspect if outsourced data is consistently cached on the rented edge nodes with agreed geo-location. We leverage timed Challenge-Response mechanisms for data possession proof while measuring verification latency to detect re-outsourcing behaviors by comparing with re-outsourcing detection threshold $\mathbb {C}$. We prove that the edge node whose verification latency exceeds $\mathbb {C}$ is dishonest. To obtain the optimal $\mathbb {C}$, we formulate the threshold determination (TD) problem and transform it to an easy-to-handle form for problem complexity reduction. Then, a preference-based approach named TD-P is developed to efficiently address the transformed TD problem. On top of that, we propose a $\mathbb {C}$C-aware edge data re-outsourcing detection scheme entitled EDRD-$\mathbb {C}$ to tackle the EDRD problem effectively. The efficiency and effectiveness of TD-P and EDRD-$\mathbb {C}$ are verified by extensive theoretical analysis and experimental evaluations on both simulated and real platforms. Notably, EDRD-$\mathbb {C}$ achieves 100% detection accuracy by sacrificing a reasonable amount of computing resources and 92.97% in the worst case.