Due to the dynamic nature of WAHN communications and the multi-node involvement in most WAHN applications, group key management has been proposed for efficient support of secure communications in WAHNs. Exclusion Basis Systems (EBS) provide a framework for scalable and efficient group key management where the number of keys per node and the number of re-key messages can be relatively adjusted. EBS-based solutions, however, may suffer from collusion attacks, where a number of nodes may collaborate to reveal all system keys and consequently capture the network. In this paper we investigate the collusion problem in EBS and demonstrate that a careful assignment of keys to nodes reduces collusion. Since an optimal assignment is NP hard, we propose a location-based heuristic where keys are assigned to neighboring nodes depending on the hamming distance between the strings of bits representing the used subset of the keys employed in the system. Simulation results have demonstrated that our proposed solution significantly boosts the network resilience to potential collusion threats.
The widespread application of deep learning has changed the landscape of computation in the data center. In particular, personalized recommendation for content ranking is now largely accomplished leveraging deep neural networks. However, despite the importance of these models and the amount of compute cycles they consume, relatively little research attention has been devoted to systems for recommendation. To facilitate research and to advance the understanding of these workloads, this paper presents a set of real-world, productionscale DNNs for personalized recommendation coupled with relevant performance metrics for evaluation. In addition to releasing a set of open-source workloads, we conduct indepth analysis that underpins future system design and optimization for at-scale recommendation: Inference latency varies by 60% across three Intel server generations, batching and co-location of inferences can drastically improve latency-bounded throughput, and the diverse composition of recommendation models leads to different optimization strategies.Preprint. Under submission.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.