k-Nearest Neighbor Query Processing Algorithms for a Query Region in Road Networks

Recent development of wireless communication technologies and the popularity of smart phones are making location-based services (LBS) popular. However, requesting queries to LBS servers with users’ exact locations may threat the privacy of users. Therefore, there have been many researches on generating a cloaked query region for user privacy protection. Consequently, an effcient query processing algorithm for a query region is required. So, in this paper, we propose k-nearest neighbor query (k-NN) processing algorithms for a query region in road networks. To effciently retrieve k-NN points of interest (POIs), we make use of the Island index. We also propose a method that generates an adaptive Island index to improve the query processing performance and storage usage. Finally, we show by our performance analysis that our k-NN query processing algorithms outperform the existing k-Range Nearest Neighbor (kRNN) algorithm in terms of network expansion cost and query processing time.     

Spatial cloaking for anonymous location-based services in mobile peer-to-peer environments

This paper tackles a privacy breach in current location-based services (LBS) where mobile users have to report their exact location information to an LBS provider in order to obtain their desired services. For example, a user who wants to issue a query asking about her nearest gas station has to report her exact location to an LBS provider. However, many recent research efforts have indicated that revealing private location information to potentially untrusted LBS providers may lead to major privacy breaches. To preserve user location privacy, spatial cloaking is the most commonly used privacy-enhancing technique in LBS. The basic idea of the spatial cloaking technique is to blur a user’s exact location into a cloaked area that satisfies the user specified privacy requirements. Unfortunately, existing spatial cloaking algorithms designed for LBS rely on fixed communication infrastructure, e.g., base stations, and centralized/distributed servers. Thus, these algorithms cannot be applied to a mobile peer-to-peer (P2P) environment where mobile users can only communicate with other peers through P2P multi-hop routing without any support of fixed communication infrastructure or servers. In this paper, we propose a spatial cloaking algorithm for mobile P2P environments. As mobile P2P environments have many unique limitations, e.g., user mobility, limited transmission range, multi-hop communication, scarce communication resources, and network partitions, we propose three key features to enhance our algorithm: (1) An information sharing scheme enables mobile users to share their gathered peer location information to reduce communication overhead; (2) A historical location scheme allows mobile users to utilize stale peer location information to overcome the network partition problem; and (3) A cloaked area adjustment scheme guarantees that our spatial cloaking algorithm is free from a “center-of-cloaked-area” privacy attack. Experimental results show that our P2P spatial cloaking algorithm is scalable while guaranteeing the user’s location privacy protection.     

Preserving location privacy without exact locations in mobile services

Privacy preservation has recently received considerable attention in location-based services (LBSs). A large number of location cloaking algorithms have been proposed for protecting the location privacy of mobile users. However, most existing cloaking approaches assume that mobile users are trusted. And exact locations are required to protect location privacy, which is exactly the information mobile users want to hide. In this paper, we propose a p-anti-conspiration privacy model to anonymize over semi-honest users. Furthermore, two k*NNG-based cloaking algorithms, vk*NNCA and ek*NNCA, are proposed to protect location privacy without exact locations. The efficiency and effectiveness of the proposed algorithms are validated by a series of carefully designed experiments. The experimental results show that the price paid for location privacy protection without exact locations is small.     

Trip planning queries with location privacy in spatial databases

Privacy has become a major concern for the users of location-based services (LBSs) and researchers have focused on protecting user privacy for different location-based queries. In this paper, we propose techniques to protect location privacy of users for trip planning (TP) queries, a novel type of query in spatial databases. A TP query enables a user to plan a trip with the minimum travel distance, where the trip starts from a source location, goes through a sequence of points of interest (POIs) (e.g., restaurant, shopping center), and ends at a destination location. Due to privacy concerns, users may not wish to disclose their exact locations to the location-based service provider (LSP). In this paper, we present the first comprehensive solution for processing TP queries without disclosing a user’s actual source and destination locations to the LSP. Our system protects the user’s privacy by sending either a false location or a cloaked location of the user to the LSP but provides exact results of the TP queries. We develop a novel technique to refine the search space as an elliptical region using geometric properties, which is the key idea behind the efficiency of our algorithms. To further reduce the processing overhead while computing a trip from a large POI database, we present an approximation algorithm for privacy preserving TP queries. Extensive experiments show that the proposed algorithms evaluate TP queries in real time with the desired level of location privacy.     

A direct boosting algorithm for the k-nearest neighbor classifier via local warping of the distance metric

Though the k-nearest neighbor (k-NN) pattern classifier is an effective learning algorithm, it can result in large model sizes. To compensate, a number of variant algorithms have been developed that condense the model size of the k-NN classifier at the expense of accuracy. To increase the accuracy of these condensed models, we present a direct boosting algorithm for the k-NN classifier that creates an ensemble of models with locally modified distance weighting. An empirical study conducted on 10 standard databases from the UCI repository shows that this new Boosted k-NN algorithm has increased generalization accuracy in the majority of the datasets and never performs worse than standard k-NN.     

基于网格划分空间的位置匿名算法

现有的位置匿名算法的匿名时间较长,匿名后的空间区域较大,严重影响查询的服务质量。为了解决这些问题,提出了一种基于网格划分空间的位置匿名算法,该算法基于位置k-匿名模型,采用网格结构划分空间后对用户位置进行位置匿名。实验结果表明,该算法在满足用户位置隐私需求的前提下,位置匿名时间更短,用户的平均匿名空间减小,从而大幅度提升用户查询的服务质量。     

Improving nearest neighbor classification with cam weighted distance

Nearest neighbor (NN) classification assumes locally constant class conditional probabilities, and suffers from bias in high dimensions with a small sample set. In this paper, we propose a novel cam weighted distance to ameliorate the curse of dimensionality. Different from the existing neighborhood-based methods which only analyze a small space emanating from the query sample, the proposed nearest neighbor classification using the cam weighted distance (CamNN) optimizes the distance measure based on the analysis of inter-prototype relationship. Our motivation comes from the observation that the prototypes are not isolated. Prototypes with different surroundings should have different effects in the classification. The proposed cam weighted distance is orientation and scale adaptive to take advantage of the relevant information of inter-prototype relationship, so that a better classification performance can be achieved. Experiments show that CamNN significantly outperforms one nearest neighbor classification (1-NN) and k-nearest neighbor classification (k-NN) in most benchmarks, while its computational complexity is comparable with that of 1-NN classification.     

Probably correct k-nearest neighbor search in high dimensions

A novel approach for k-nearest neighbor (k-NN) searching with Euclidean metric is described. It is well known that many sophisticated algorithms cannot beat the brute-force algorithm when the dimensionality is high. In this study, a probably correct approach, in which the correct set of k-nearest neighbors is obtained in high probability, is proposed for greatly reducing the searching time. We exploit the marginal distribution of the k th nearest neighbors in low dimensions, which is estimated from the stored data (an empirical percentile approach). We analyze the basic nature of the marginal distribution and show the advantage of the implemented algorithm, which is a probabilistic variant of the partial distance searching. Its query time is sublinear in data size n, that is, O(mnδ) with δ=o(1) in n and δ≤1, for any fixed dimension m.     

Query-aware location anonymization for road networks

Recently, several techniques have been proposed to protect the user location privacy for location-based services in the Euclidean space. Applying these techniques directly to the road network environment would lead to privacy leakage and inefficient query processing. In this paper, we propose a new location anonymization algorithm that is designed specifically for the road network environment. Our algorithm relies on the commonly used concept of spatial cloaking, where a user location is cloaked into a set of connected road segments of a minimum total length L{\cal L} including at least K{\cal K} users. Our algorithm is “query-aware” as it takes into account the query execution cost at a database server and the query quality, i.e., the number of objects returned to users by the database server, during the location anonymization process. In particular, we develop a new cost function that balances between the query execution cost and the query quality. Then, we introduce two versions of our algorithm, namely, pure greedy and randomized greedy, that aim to minimize the developed cost function and satisfy the user specified privacy requirements. To accommodate intervals with a high workload, we introduce a shared execution paradigm that boosts the scalability of our location anonymization algorithm and the database server to support large numbers of queries received in a short time period. Extensive experimental results show that our algorithms are more efficient and scalable than the state-of-the-art technique, in terms of both query execution cost and query quality. The results also show that our algorithms have very strong resilience to two privacy attacks, namely, the replay attack and the center-of-cloaked-area attack.     

Approximate and exact hybrid algorithms for private nearest-neighbor queries with database protection

Mobile devices with global positioning capabilities allow users to retrieve points of interest (POI) in their proximity. To protect user privacy, it is important not to disclose exact user coordinates to un-trusted entities that provide location-based services. Currently, there are two main approaches to protect the location privacy of users: (i) hiding locations inside cloaking regions (CRs) and (ii) encrypting location data using private information retrieval (PIR) protocols. Previous work focused on finding good trade-offs between privacy and performance of user protection techniques, but disregarded the important issue of protecting the POI dataset D. For instance, location cloaking requires large-sized CRs, leading to excessive disclosure of POIs (O(|D|) in the worst case). PIR, on the other hand, reduces this bound to \(O(\sqrt{|D|})\), but at the expense of high processing and communication overhead. We propose hybrid, two-step approaches for private location-based queries which provide protection for both the users and the database. In the first step, user locations are generalized to coarse-grained CRs which provide strong privacy. Next, a PIR protocol is applied with respect to the obtained query CR. To protect against excessive disclosure of POI locations, we devise two cryptographic protocols that privately evaluate whether a point is enclosed inside a rectangular region or a convex polygon. We also introduce algorithms to efficiently support PIR on dynamic POI sub-sets. We provide solutions for both approximate and exact NN queries. In the approximate case, our method discloses O(1) POI, orders of magnitude fewer than CR- or PIR-based techniques. For the exact case, we obtain optimal disclosure of a single POI, although with slightly higher computational overhead. Experimental results show that the hybrid approaches are scalable in practice, and outperform the pure-PIR approach in terms of computational and communication overhead.     

Countering overlapping rectangle privacy attack for moving kNN queries

An important class of LBSs is supported by the moving k nearest neighbor (MkNN) query, which continuously returns the k nearest data objects for a moving user. For example, a tourist may want to observe the five nearest restaurants continuously while exploring a city so that she can drop in to one of them anytime. Using this kind of services requires the user to disclose her location continuously and therefore may cause privacy leaks derived from the user's locations. A common approach to protecting a user's location privacy is the use of imprecise locations (e.g., regions) instead of exact positions when requesting LBSs. However, simply updating a user's imprecise location to a location-based service provider (LSP) cannot ensure a user's privacy for an MkNN query: continuous disclosure of regions enable LSPs to refine more precise location of the user. We formulate this type of attack to a user's location privacy that arises from overlapping consecutive regions, and provide the first solution to counter this attack. Specifically, we develop algorithms which can process an MkNN query while protecting the user's privacy from the above attack. Extensive experiments validate the effectiveness of our privacy protection technique and the efficiency of our algorithm.     

Manifold-ranking based retrieval using k-regular nearest neighbor graph

Manifold-ranking is a powerful method in semi-supervised learning, and its performance heavily depends on the quality of the constructed graph. In this paper, we propose a novel graph structure named k-regular nearest neighbor (k-RNN) graph as well as its constructing algorithm, and apply the new graph structure in the framework of manifold-ranking based retrieval. We show that the manifold-ranking algorithm based on our proposed graph structure performs better than that of the existing graph structures such as k-nearest neighbor (k-NN) graph and connected graph in image retrieval, 2D data clustering as well as 3D model retrieval. In addition, the automatic sample reweighting and graph updating algorithms are presented for the relevance feedback of our algorithm. Experiments demonstrate that the proposed algorithm outperforms the state-of-the-art algorithms.     

Top-n query processing in spatial databases considering bi-chromatic reverse k-nearest neighbors

A reverse k-nearest neighbor (RkNN) query retrieves the data points which regard the query point as one of their respective k nearest neighbors. A bi-chromatic reverse k-nearest neighbor (BRkNN) query is a variant of the RkNN query, considering two types of data. Given two types of data G and C, a BRkNN query regarding a data point q in G retrieves the data points from C that regard q as one of their respective k-nearest neighbors among the data points in G. Many existing approaches answer either the RkNN query or the BRkNN query. Different from these approaches, in this paper, we make the first attempt to propose a top-n query based on the concept of BRkNN queries, which ranks the data points in G and retrieves the top-n points according to the cardinalities of the corresponding BRkNN answer sets. For efficiently answering this top-n query, we construct the Voronoi Diagram of G to index the data points in G and C. From the information associated with the Voronoi Diagram of G, the upper bound of the cardinality of the BRkNN answer sets for each data point in G can be quickly computed. Moreover, based on an existing approach to answering the RkNN query and the characteristics of the Voronoi Diagram of G, we propose a method to find the candidate region regarding a BRkNN query, which tightens the corresponding search space. Finally, based on the triangle inequality, we propose an efficient refinement algorithm for finding the exact BRkNN answers from the candidate regions. To evaluate our approach on answering the top-n query, it is compared with an approach which applies a state-of-the-art algorithm for answering the BRkNN query to each data point in G. The experiment results reveal that our approach has a much better performance.     

Chromatic distribution of k-nearest neighbors of a line segment in a planar colored point set

Let P be a set of n colored points distributed arbitrarily in R². The chromatic distribution of the k-nearest neighbors of a query line segment ? is to report the number of points of each color among the k-nearest points of the query line segment. While solving this problem, we have encountered another interesting problem, namely the semicircular range counting query. Here a set of n points is given. The objective is to report the number of points inside a given semicircular range. We propose a simple algorithm for this problem with preprocessing time and space complexity O(n³), and the query time complexity O(logn). Finally, we propose the algorithm for reporting the chromatic distribution of k nearest neighbors of a query line segment. Using our proposed technique for semicircular range counting query, it runs in O(log²n) time.     

A multi-resolution surface distance model for <Emphasis Type="Italic">k</Emphasis>-NN query processing

A spatial k-NN query returns k nearest points in a point dataset to a given query point. To measure the distance between two points, most of the literature focuses on the Euclidean distance or the network distance. For many applications, such as wildlife movement, it is necessary to consider the surface distance, which is computed from the shortest path along a terrain surface. In this paper, we investigate the problem of efficient surface k-NN (sk-NN) query processing. This is an important yet highly challenging problem because the underlying environment data can be very large and the computational cost of finding the shortest path on a surface can be very high. To minimize the amount of surface data to be used and the cost of surface distance computation, a multi-resolution surface distance model is proposed in this paper to take advantage of monotonic distance changes when the distances are computed at different resolution levels. Based on this innovative model, sk-NN queries can be processed efficiently by accessing and processing surface data at a just-enough resolution level within a just-enough search region. Our extensive performance evaluations using real world datasets confirm the efficiency of our proposed model.     

保护位置隐私和查询内容隐私的路网K近邻查询方法

位置隐私和查询内容隐私是LBS兴趣点（point of interest,简称POI）查询服务中需要保护的两个重要内容,同时,在路网连续查询过程中,位置频繁变化会给LBS服务器带来巨大的查询处理负担,如何在保护用户隐私的同时,高效地获取精确查询结果,是目前研究的难题.以私有信息检索中除用户自身外其他实体均不可信的思想为基本假设,基于Paillier密码系统的同态特性,提出了无需用户提供真实位置及查询内容的K近邻兴趣点查询方法,实现了对用户位置、查询内容隐私的保护及兴趣点的精确检索;同时,以路网顶点为生成元组织兴趣点分布信息,进一步解决了高强度密码方案在路网连续查询中因用户位置变化频繁导致的实用效率低的问题,减少了用户的查询次数,并能确保查询结果的准确性.最后从准确性、安全性及查询效率方面对本方法进行了分析,并通过仿真实验验证了理论分析结果的正确性.     

Direction-aware KNN queries for moving objects in a road network

Recently more and more people focus on k-nearest neighbor (KNN) query processing over moving objects in road networks, e.g., taxi hailing and ride sharing. However, as far as we know, the existing k-nearest neighbor (KNN) queries take distance as the major criteria for nearest neighbor objects, even without taking direction into consideration. The main issue with existing methods is that moving objects change their locations and directions frequently over time, so the information updates cannot be processed in time and they run the risk of retrieving the incorrect KNN results. They may fail to meet users’ needs in certain scenarios, especially in the case of querying k-nearest neighbors for moving objects in a road network. In order to find the top k-nearest objects moving toward a query point, this paper presents a novel algorithm for direction-aware KNN (DAKNN) queries for moving objects in a road network. In this method, R-tree and simple grid are firstly used as the underlying index structure, where the R-tree is used for indexing the static road network and the simple grid is used for indexing the moving objects. Then, it introduces the notion of “azimuth” to represent the moving direction of objects in a road network, and presents a novel local network expansion method to quickly judge the direction of the moving objects. By considering whether a moving object is moving farther away from or getting closer to a query point, the object that is definitely not in the KNN result set is effectively excluded. Thus, we can reduce the communication cost, meanwhile simplify the computation of moving direction between moving objects and query point. Comprehensive experiments are conducted and the results show that our algorithm can achieve real-time and efficient queries in retrieving objects moving toward query point in a road network.

     

Privacy-Conscious Location-Based Queries in Mobile Environments

In location-based services, users with location-aware mobile devices are able to make queries about their surroundings anywhere and at any time. While this ubiquitous computing paradigm brings great convenience for information access, it also raises concerns over potential intrusion into user location privacy. To protect location privacy, one typical approach is to cloak user locations into spatial regions based on user-specified privacy requirements, and to transform location-based queries into region-based queries. In this paper, we identify and address three new issues concerning this location cloaking approach. First, we study the representation of cloaking regions and show that a circular region generally leads to a small result size for region-based queries. Second, we develop a mobility-aware location cloaking technique to resist trace analysis attacks. Two cloaking algorithms, namely MaxAccu_Cloak and MinComm_Cloak, are designed based on different performance objectives. Finally, we develop an efficient polynomial algorithm for evaluating circular-region-based kNN queries. Two query processing modes, namely bulk and progressive, are presented to return query results either all at once or in an incremental manner. Experimental results show that our proposed mobility-aware cloaking algorithms significantly improve the quality of location cloaking in terms of an entropy measure without compromising much on query latency or communication cost. Moreover, the progressive query processing mode achieves a shorter response time than the bulk mode by parallelizing the query evaluation and result transmission.     

Decomposable algorithm for computing k-nearest neighbours across partitioned data

A common constraint in distributed data is that the database cannot be moved to other network sites due to computational costs, data size, or privacy considerations. All of the existing distributed algorithms for computing k-nearest neighbours (k-NNs) are designed for horizontally partitioned or special case of vertically partitioned data where different sites contain different attributes for a common set of entities. In this article, we present a framework including a general model and a decomposable algorithm for computing k-NN in d-dimensional space across horizontally and vertically partitioned data in the most general situation in which existing distributed databases want to cooperate for k-NN. The key is to obtain valid results, with a minimum information disclosure. The proposed algorithm preserves the privacy of the data at individual sites by requiring transmission of only minimal information to other sites. The computation is performed by exchanging minimum number of higher level summaries so that even if they are captured by an intruder to actual data tuples can ever be revealed.