{MrLazy}: Lazy Runtime Label Propagation for {MapReduce}
6th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 14), 2014•usenix.org
… We only track lineage during computation, which we use to construct output labels and
enforce policies retrospectively when data is about to leave the trust domain. In this paper
we present MrLazy, a prototype system that implements lazy label propagation for Hadoop
MapReduce. We choose MapReduce because it is a popular computation framework in the
Cloud. Our preliminary evaluations show that …
enforce policies retrospectively when data is about to leave the trust domain. In this paper
we present MrLazy, a prototype system that implements lazy label propagation for Hadoop
MapReduce. We choose MapReduce because it is a popular computation framework in the
Cloud. Our preliminary evaluations show that …
Abstract
Organisations are starting to publish datasets containing potentially sensitive information in the Cloud; hence it is important there is a clear audit trail to show that involved parties are respecting data sharing laws and policies.
usenix.org