|
|
|
| e-Pub |
Previous | 
Home
Section: New Results
Query Processing
Top-k Query Processing Over Encrypted Data in the Cloud
Participants : Sakina Mahboubi, Reza Akbarinia, Patrick Valduriez.
Cloud computing provides users and companies with powerful capabilities to store and process their data in third-party data centers. However, the privacy of the outsourced data is not guaranteed by the cloud providers. One solution for protecting the user data against security attacks is to encrypt the data before being sent to the cloud servers. Then, the main problem is to evaluate user queries over the encrypted data.
In this work, we address the problem of top-k query processing over encrypted data. Top-k queries are important for many applications such as information retrieval, spatial data analysis, temporal databases, graph databases, etc. We consider two cases for top-k query processing over encrypted data: 1) centralized: the encrypted data are stored at a single node of a data center, which is useful if the database can fit at one node; 2) distributed: the encrypted data are partitioned and the partitions are encrypted and distributed across multiple nodes, which is useful if the database is very big.
In [52], we address the distributed case, and propose a system, called SD-TOPK, for top-k query processing over encrypted data distributed across several nodes of the cloud. SD-TOPK comes with a distributed top-k query processing algorithm that is executed in the nodes, and finds a set including the encrypted top-k data items. It also has an efficient filtering algorithm that removes most of the false positives included in the set returned by the top-k query processing algorithm. This filtering is done without needing to decrypt the data in the cloud.
In [51], we propose a complete system, called BuckTop, for the centralized case. BuckTop is able to efficiently evaluate top-k queries over encrypted data outsourced to a singe node, without having to decrypt it in that node. It includes a top-k query processing algorithm that works on the encrypted data stored in the cloud node, and returns a set that is proved to contain the encrypted data corresponding to the top-k results. We implemented BuckTop and compared its performance for processing top-k queries over encrypted data with that of the popular threshold algorithm (TA) over original (plaintext) data. The results show the effectiveness of BuckTop for outsourcing sensitive data in the cloud and answering top-k queries.
Privacy Preserving Index for Range Query Processing in the Clouds
Participants : Reza Akbarinia, Esther Pacitti.
During the last decade, a large body of academic work has tackled the problem of outsourcing databases to an untrusted cloud while maintaining both privacy and SQL-like querying functionality (at least partially). Range query is an important kind of query that expresses a bounded restriction over the retrieved records. In the database management systems, these queries are usually answered by using efficient indexes. However, developing privacy preserving indexes for untrusted environments is very challenging.
In [55], we propose a differentially private index to an outsourced encrypted dataset. Efficiency is enabled by using a plaintext index structure to perform range queries. Security relies on both differential privacy (of the index) and semantic security (of the encrypted dataset). Our solution, called PINED-RQ, develops algorithms for building and updating the differentially private index. Compared to state-of-the-art secure index based range query processing approaches, PINED-RQ executes queries in the order of at least one magnitude faster. The security of PINED-RQ is proved and its efficiency is assessed by an extensive experimental validation.
Constellation Queries to Analyze Geometrical Patterns
Participants : Dennis Shasha, Patrick Valduriez.
Constellation queries are useful to analyze geometrical patterns. A geometrical pattern is a set of points with all pairwise distances (or, more generally, relative distances) specified. Finding matches to such patterns, i.e. constellations, has applications to spatial data in seismic, astronomical, and transportation contexts. Finding geometric patterns is a challenging problem as the potential number of sets of elements that compose shapes is exponentially large in the size of the dataset and the pattern. In [53], we propose algorithms to find patterns in large data applications using constellation queries. Our methods combine quadtrees, matrix multiplication, and bucket join processing. Our distributed experiments show that the choice of the composition algorithm (matrix multiplication or nested loops) depends on the freedom introduced in the query geometry through the distance additive factor. Three clearly identified blocks of threshold values guide the choice of the best composition algorithm. Answering complex constellation queries, i.e. isotropic and non-isotropic queries, is challenging because scale factors and stretch factors may take any of an infinite number of values. In [53], we propose practically efficient sequential and distributed algorithms for pure, isotropic, and non-isotropic constellation queries. As far as we know, this is the first work to address isotropic and non-isotropic queries.
Parallel Polyglot Query Processing
Participants : Boyan Kolev, Oleksandra Levchenko, Esther Pacitti, Patrick Valduriez.
The blooming of different cloud data stores has turned polystore systems to a major topic in the nowadays cloud landscape. Especially, as the amount of processed data grows rapidly each year, much attention is being paid on taking advantage of the parallel processing capabilities of the underlying data stores. To provide data federation, a typical polystore solution defines a common data model and query language with translations to API calls or queries to each data store. However, this may lead to losing important querying capabilities. The polyglot approach of the CloudMdsQL query language allows data store native queries to be expressed as inline scripts and combined with regular SQL statements in ad-hoc integration queries. Moreover, efficient optimization techniques, such as bind join, can still take place to improve the performance of selective joins. In [47], we introduce the distributed architecture of the LeanXcale query engine that processes polyglot queries in the CloudMdsQL query language, yet allowing native scripts to be handled in parallel at data store shards, so that efficient and scalable parallel joins take place at the query engine level. The experimental evaluation of the LeanXcale parallel query engine on various join queries illustrates well the performance benefits of exploiting the parallelism of the underlying data management technologies in combination with the high expressivity provided by their scripting/querying frameworks