Consumer data, such as documents and photos, are increasingly being stored in the cloud. To ensure confidentiality, the data is encrypted before being outsourced. However, this makes it difficult to search the encrypted data directly. Recent approaches to enable searching of this encrypted data have relied on trapdoors, locally stored indexes, and homomorphic encryption. However, data communication cost for these techniques is very high and they limit search capabilities either to a small set of pre-defined trapdoors or only allow exact keyword matching. This paper addresses the problem of high communication cost of bloom-filter based privacy-preserving search for measuring similarity between the search query and the encrypted data. We propose a novel compression algorithm which avoids the need to send the entire encrypted bloom filter index back to the client. This reduces the cost of communicating results to the client by over 95%. Using sliding window bloom filters and homomorphic encryption also enables our system to search over encrypted data using keywords that only partially match the originally stored words. We demonstrate the viability of our system by implementing it on Google Cloud, and our results show that the cost of partially matching search queries on encrypted data scales linearly with the total number of keywords stored on the server.

As data continues to be generated at exponentially growing rates in heterogeneous formats, fast analytics to extract meaningful information is becoming increasingly important. Systems widely use in-memory caching as one of their primary techniques to speed up data analytics. However, caches in data analytics systems cannot rely on simple caching policies and a fixed data layout to achieve good performance. Different datasets and workloads require different layouts and policies to achieve optimal performance. This paper presents ReCache, a cache-based performance accelerator that is reactive to the cost and heterogeneity of diverse raw data formats. Using timing measurements of caching operations and selection operators in a query plan, ReCache accounts for the widely varying costs of reading, parsing, and caching data in nested and tabular formats. Combining these measurements with information about frequently accessed data fields in the workload, ReCache automatically decides whether a nested or relational column-oriented layout would lead to better query performance. Furthermore, ReCache keeps track of commonly utilized operators to make informed cache admission and eviction decisions. Experiments on synthetic and real-world datasets show that our caching techniques decrease caching overhead for individual queries by an average of 59%. Furthermore, over the entire workload, ReCache reduces execution time by 19-75% compared to existing techniques.

Virtual worlds and games increasingly deliver 3D meshes over the Internet using instanced file formats, such as COLLADA. However, existing simplification algorithms do not account for instancing in their inputs, operating instead on triangle soups or indexed triangle meshes. This makes them unsuitable for highly instanced meshes, since expanding an instanced mesh to an indexed triangle mesh and then simplifying it can result in a larger output file size. The high cost of delivering these larger files over the Internet results in long network latencies and low performance. This paper presents instance-aware simplification (IAS), an algorithm designed to efficiently simplify instanced 3D meshes. To ensure smaller output file sizes, IAS incorporates the existing compression of mesh instancing into its cost metrics. Unlike existing algorithms, IAS strictly reduces file size as it simplifies, so that IAS-simplified meshes of a given file size have higher visual quality than meshes simplified using existing algorithms. On highly instanced models, IAS results in simplified versions that are orders of magnitude smaller than existing algorithms for a given triangle count.

Unlike most graphics systems, a shared, user-generated virtual world is created on-the-fly by end users rather than professional artists. Objects in the world can come and go, and the world can be composed of so many models and textures that it cannot be stored locally on disk. The content must be stored in a shared, networked resource such as the cloud and delivered to clients dynamically.

This paper explores metrics that capture to what degree packet reception on different links is correlated. Specifically, it explores metrics that shed light on when and why opportunistic routing and network coding protocols perform well (or badly). It presents a new metric, κ that, unlike existing widely used metrics, has no bias based on the packet reception ratios of links. This lack of bias makes κ a better predictor of performance of opportunistic routing and network coding protocols. Comparing Deluge and Rateless Deluge, Deluge's network coding counterpart, we find that κ can predict which of the two is best suited for a given environment. For example, irrespective of the packet reception ratios of the links, if the average κ of the link pairs is very high (close to 1.0), then using a protocol that does not code works better than using a network coding protocol. Measuring κ on several 802.15.4 and 802.11 testbeds, we find that it varies significantly across network topologies and link layers. κ can be a metric for quantifying what kind of a network is present and help decide which protocols to use for that network.

We present the Whirlpool Routing Protocol (WARP), which efficiently routes data to a node moving within a static mesh. The key insight in WARP's design is that data traffic can use an existing routing gradient to efficiently probe the topology, repair the routing gradient, and communicate these repairs to nearby nodes.

We present Starburst, a routing-based protocol designed to efficiently disseminate data items to small subsets within a sensor network. Starburst constructs a routing hierarchy to enable fast, efficient and reliable dissemination to nodes in a sensor network that satisfy data-specific predicates. The protocol is based on the idea that when only a few nodes need an update, it is more efficient and much faster to route to those nodes directly. When every node needs an update, algorithms such as Trickle are more efficient. Starburst therefore dynamically determines what portion of nodes need an update and locally adapts its delivery policy accordingly. We also present dynamic beacon selection algorithms which enable scalability and fault tolerance in Starburst. We have implemented and evaluated Starburst on top of both the BVR and S4 routing protocols with promising results. Our simulations show that Starburst reduces both the transmission cost and latency of existing dissemination protocols by at least 50% for small subsets of nodes, and performs no worse than them for larger sets. Finally, tests on the Motelab testbed validate our simulation results.

High energy physics (HEP) and other scientific communities have adopted service oriented architectures (SOA) as part of a larger grid computing effort. This effort involves the integration of many legacy applications and programming libraries into a SOA framework. The grid analysis environment (GAE) (Lingen et al., 2004) is such a service oriented architecture based on the Clarens grid services framework (Steenberg et al., 2004) and is being developed as part of the compact muon solenoid (CMS) experiment at the large hadron collider (LHC) at European Laboratory for Particle Physics (CERN). Clarens provides a set of authorization, access control, and discovery services, as well as XMLRPC and SOAP access to all deployed services. Two implementations of the Clarens Web services framework (Python and Java) offer integration possibilities for a wide range of programming languages. This paper describes the Java implementation of the Clarens Web services framework called 'JClarens' and several Web services of interest to the scientific and grid community that have been deployed using JClarens.

In this paper we describe JClarens; a Java based implementation of the Clarens remote data server. JClarens provides Web services for an interactive analysis environment to dynamically access and analyze the tremendous amount of data scattered across various locations. Additionally this research is aimed to develop a service oriented grid enabled portal (GEP) that provides interface and access to several grid services to give a homogeneous and optimized view of the distributed and heterogeneous environment. Other than showing platform independent behavior provided by Java, the use of XML-RPC based Web services enabled JClarens to be a language neutral server and demonstrated interoperability with its Python variant. Extreme care has been taken in the usage and manipulation of various Java libraries to cater the needs of high performance computing. The overall exercise has yielded in a prototype with strong emphasis on security and virtual organization management (VOM). This shall provide a common platform to support development of larger, more flexible framework with future aims to integrate it with a loosely coupled, decentralized, and autonomous framework for grid enabled analysis environment (GAE).