عنوان انگلیسی مقاله:
Pipeline-integrity: Scaling the use of authenticated data structures up to the cloud
ترجمه فارسی عنوان مقاله:
پایپ لاین-یکپارچگی: مقیاس استفاده از ساختارهای داده معتبر تا ابر
Sciencedirect - Elsevier - Future Generation Computer Systems, 100 (2019) 618-647: doi:10:1016/j:future:2019:05:018
Diego Pennino, Maurizio Pizzonia ∗, Federico Griscioli
Public cloud storage services are widely adopted for their scalability and low cost. However, delegating
the management of the storage has serious implications from the security point of view. We focus
on integrity verification of query results based on the use of Authenticated Data Structures (ADS).
An ADS enables efficient updates of a cryptographic digest, when data changes, and efficient query
verification against this digest. Since, the digest can be updated (and usually signed) exclusively with
the intervention of a trusted party, the adoption of this approach is source of a serious performance
degradation, in particular when the trusted party is far from the server that stores the ADS.
In this paper, we show a protocol for a key–value storage service that provides ADS-enabled
integrity-protected queries and updates without impairing scalability, even in the presence of large
network latencies between trusted clients and an untrusted server. Our solution complies with the
principle of the cloud paradigm in which services should be able to arbitrarily scale with respect to
number of clients, requests rates, and data size keeping response time limited. We formally prove
that our approach is able to detect server misbehaviour in a setting whose consistency rules are only
slightly weaker than those guaranteed by previous results. We provide experimental evidence for the
feasibility and scalability of our approach.
Keywords: Authenticated data structures | Scalability | Cloud | Integrity | Pipeline | Fork-linearisability