Privacy Protection Approach Research Articles

A human-centered artificial intelligence approach for privacy protection of elderly App users in smart cities

Artificial Intelligence and Machine Learning based Ambient Assisted Living systems play an important role in smart cities by improving the quality of life of the elderly population. Many Ambient Assisted Living systems are coupled with Android Apps for command-and-control purposes. Consequently, the privacy and security of Ambient Assisted Living systems depend on the privacy and security of the corresponding Android Apps, which follow a privacy self-management model. Unfortunately, the privacy self-management model ignores the decision-making abilities of the elderly and increases their cognitive loads, which put their privacy protection and wellbeing at stake. In this paper, we follow a Human-Centered Artificial Intelligence inspired approach for addressing these issues. This approach uses privacy as a shared responsibility model instead of the privacy self-management model. We have proposed two algorithms, the participatory privacy protection algorithm-I, and participatory privacy protection algorithm-II, for determining optimal privacy settings of an Ambient Assisted Living App and handling its runtime Permission requests, respectively. We demonstrated the working of these algorithms using a case study. We have also compared the proposed approach with state-of-the-art privacy management schemes for Android Apps. The proposed algorithms can improve the privacy protection of Ambient Assisted Living App users in smart cities and relieve them through cognitive offloading.

Privacy-Preserving Boosting in the Local Setting

In machine learning, boosting is one of the most popular methods that is designed to combine multiple base learners into a superior one. The well-known Boosted Decision Tree classifier has been widely adopted in data mining and pattern recognition. With the emerging challenge in privacy, the personal images, browsing history, and financial reports, which are held by individuals and entities are more likely to contain sensitive information. The privacy concern is intensified when the data leaves the hand of owners and is used for further mining. Such privacy issues demand that the machine learning algorithms should be privacy-aware. Recently, Local Differential Privacy has been proposed as an effective privacy protection approach, which allows data owners to perturb the data before any release. In this paper, we propose a distributed privacy-preserving boosting algorithm that can be applied to various types of classifiers. By adopting LDP as a building block, the proposed boosting algorithm leverages the aggregation of the perturbed data shares to build the base learner, which ensures that privacy is well preserved for the participated data owners. Our experiments demonstrate that the proposed algorithm effectively boosts various classifiers and the boosted classifiers maintain a high utility.

Privacy Preserving Spatio-Temporal Databases Based on k-Anonymity

The development of location-based services and mobile devices has lead to an increase in the location data. Through the data mining process, some valuable information can be discovered from location data. In the other words, an attacker may also extract some private (sensitive) information of the user and this may make threats against the user privacy. Therefore, location privacy protection becomes an important requirement to the success in the development of location-based services. In this paper, we propose a grid-based approach as well as an algorithm to guarantee k-anonymity, a well-known privacy protection approach, in a location database. The proposed approach considers only the information that has significance for the data mining process while ignoring the un-related information. The experiment results show the effectiveness of the proposed approach in comparison with the literature ones.

A User-Oriented Approach and Tool for Security and Privacy Protection on the Web

We introduce a novel approach to protecting the privacy of web users. We propose to monitor the behaviors of JavaScript code within a web origin based on the source of the code, i.e., code origin, to detect and prevent malicious actions that would compromise users’ privacy. Our code-origin policy enforcement approach not only advances the conventional same-origin policy standard but also goes beyond the “all-or-nothing” contemporary ad-blockers and tracker-blockers. In particular, our monitoring mechanism does not rely on browsers’ network request interception and blocking as in existing blockers. In contrast, we monitor the code that reads or sends user data sent out of the browser to enforce fine-grained and context-aware policies based on the origin of the code. We implement a proof-of-concept prototype and perform practical evaluations to demonstrate the effectiveness of our approach. Our experimental results evidence that the proposed method can detect and prevent data leakage channels not captured by the leading tools such as Ghostery and uBlock Origin. We show that our prototype is compatible with major browsers and popular real-world websites with promising runtime performance. Although implemented as a browser extension, our approach is browser-agnostic and can be integrated into the core of a browser as it is based on standard JavaScript.

A Symbiotic Relationship Based Leader Approach for Privacy Protection in Location Based Services

Location-based services (LBS) form the main part of the Internet of Things (IoT) and have received a significant amount of attention from the research community as well as application users due to the popularity of wireless devices and the daily growth in users. However, there are several risks associated with the use of LBS-enabled applications, as users are forced to send their queries based on their real-time and actual location. Attacks could be applied by the LBS server itself or by its maintainer, which consequently may lead to more serious issues such as the theft of sensitive and personal information about LBS users. Due to this fact, complete privacy protection (location and query privacy protection) is a critical problem. Collaborative (cache-based) approaches are used to prevent the LBS application users from connecting to the LBS server (malicious parties). However, no robust trust approaches have been provided to design a trusted third party (TTP), which prevents LBS users from acting as an attacker. This paper proposed a symbiotic relationship-based leader approach to guarantee complete privacy protection for users of LBS-enabled applications. Specifically, it introduced the mutual benefit underlying the symbiotic relationship, dummies, and caching concepts to avoid dealing with untrusted LBS servers and achieve complete privacy protection. In addition, the paper proposed a new privacy metric to predict the closeness of the attacker to the moment of her actual attack launch. Compared to three well-known approaches, namely enhanced dummy location selection (enhanced-DLS), hiding in a mobile crowd, and caching-aware dummy selection algorithm (enhanced-CaDSA), our experimental results showed better performance in terms of communication cost, resistance against inferences attacks, and cache hit ratio.

Privacy-Preserving Approach PBCN in Social Network With Differential Privacy

Currently, lots of real social relations in social networks force users to face the potential risk of privacy leakage. Consequently, data holders would like to disturbor anonymize their individual data before publishing them, for the purpose of privacy protection. Due to the characteristics of high sensitivity and large volume data of social network graph structure, it is difficult for privacy protection schemes to enable a reasonable allocation of noises while keeping desirable data availability and execution efficiency. On the basis of differential privacy model, combining with clustering and randomization algorithms, a privacy protection approach PBCN (Privacy Preserving Approach Based on Clustering and Noise) is proposed. This proposal is composed of five algorithms including random disturbance based on clustering, graph reconstruction after disturbing degree sequence and noise nodes generation, etc. Furthermore, a privacy measure algorithm based on adjacency degree is put forward in order to objectively evaluate the privacy-preserving strength of various schemes against graph structure and degree attacks. Simulation experiments are conducted to achieve performance comparisons between PBCN, Spctr Add/Del, Spctr Switch, DER and HPDP. The experimental results show that PBCN realizes more satisfactory data availability and execution efficiency. Finally, parameters utility analysis demonstrates PBCN can achieve a “trade-off” between data availability and privacy protection level.

A dummy-based user privacy protection approach for text information retrieval

Text retrieval enables people to efficiently obtain the desired data from massive text data, so has become one of the most popular services in information retrieval community. However, while providing great convenience for users, text retrieval results in a serious issue on user privacy. In this paper, we propose a dummy-based approach for text retrieval privacy protection. Its basic idea is to use well-designed dummy queries to cover up user queries and thus protect user privacy. First, we present a client-based system framework for the protection of user privacy, which requires no change to the existing algorithm of text retrieval, and no compromise to the accuracy of text retrieval. Second, we define a user privacy model to formulate the requirements that ideal dummy queries should meet, i.e., (1) having highly similar feature distributions with user queries, and (2) effectively reducing the significance of user query topics. Third, by means of the knowledge derived from Wikipedia, we present an implementation algorithm to construct a group of ideal dummy queries that can well meet the privacy model. Finally, we demonstrate the effectiveness of our approach by theoretical analysis and experimental evaluation. The results show that by constructing dummy queries that have similar feature distributions but unrelated topics with user queries, the privacy behind users’ textual queries can be effectively protected, under the precondition of not compromising the accuracy and usability of text retrieval.

Electronic Personal Health Records and the Question of Privacy

Personal health records (PHRs), centralized places for consumers to electronically store, manage, and share their personal health information, offer new opportunities to help consumers manage their own health and health care. However, ensuring the privacy and confidentiality of health information contained within PHRs is challenging. This paper analyzes the major properties of existing PHR systems and identifies specific privacy and security issues with each type of PHR. It proposes a consumer-controlled privacy protection approach that includes high-minded privacy principles such as independent consent management, independent privacy and security audits, and regulatory compliance requirements. It further presents a consumer-controlled system architecture that embodies these principles in the web-based PHR system.

A Double Obfuscation Approach for Protecting the Privacy of IoT Location Based Applications

Connected vehicles and smart cars have become highly reliant on location-based services (i.e. LBS) to provide accurate, personalized and intelligent services. However, location-based services have endangered its users to considerable risks concerning the privacy and security of users' personal data. Although existing research provides a myriad of methods to improve and protect user privacy in LBS applications, most of these methods are concerned with handling static queries and non-mobile objects only. Moreover, various issues and challenges still persist with regards to the need to trust third parties, overloading of the user, and low accuracy of the returned results. This paper contributes a Double Obfuscation Approach (referred to as DOA) that applies two phases of obfuscation consecutively whilst integrating two differing privacy protection approaches, namely Obfuscation and Trusted Third Party, and two techniques, namely fog caching technology and mix zone. In essence, the DOA obfuscates and hides the identity and location of its users using the fog nodes, which operate as a trusted third party (TTP), and without the need to reveal the identity of the users or trust the cooperating nodes. Moreover, this paper presents a DOA algorithm that improves the overall user privacy and system performance using the fog nodes, which split the responses of each query into five parts, thus reducing the processing time of the results by the user and enhancing the overall accuracy where the user directly selects the most suitable parts based on his current location. Overall, the hybrid DOA approach empowers the users of connected vehicle applications to protect their privacy through an algorithm that caters for the dynamic nature of user queries and mobility of objects. The results of our comparative simulations against well-known hybrid privacy protection methods demonstrate the superiority of the proposed Double Obfuscation Approach especially with respect to user privacy whilst maintaining a nominal overhead on the user, reduced response time and high accuracy of the obtained results.

A privacy protection approach for XML-based archives management in a cloud environment

PurposeThe security of archival privacy data in the cloud has become the main obstacle to the application of cloud computing in archives management. To this end, aiming at XML archives, this paper aims to present a privacy protection approach that can ensure the security of privacy data in the untrusted cloud, without compromising the system availability.Design/methodology/approachThe basic idea of the approach is as follows. First, the privacy data before being submitted to the cloud should be strictly encrypted on a trusted client to ensure the security. Then, to query the encrypted data efficiently, the approach constructs some key feature data for the encrypted data, so that each XML query defined on the privacy data can be executed correctly in the cloud.FindingsFinally, both theoretical analysis and experimental evaluation demonstrate the overall performance of the approach in terms of security, efficiency and accuracy.Originality/valueThis paper presents a valuable study attempting to protect privacy for the management of XML archives in a cloud environment, so it has a positive significance to promote the application of cloud computing in a digital archive system.

A novel Map-Scan-Reduce based density peaks clustering and privacy protection approach for large datasets

Large dataset clustering is a major research issue due to huge processing time. Clustering methods goal at split large dataset into number of groups and each group consists of similar data points. Numerous clustering methods such as partition-based clustering, hierarchical clustering, density-based clustering, spectral clustering, and subspace clustering are presented. These methods failed to produce true (accurate) clusters in less response time. To mitigate the issues of existing methods, in this paper, we propose a novel Map-Scan-Reduce based density peaks (DP) clustering approach to cluster the large datasets. MapReduce is a popular distributed processing framework that has several advantages: it has the ability to resolve any issues that arise with large data volume and it partitioned data in a distributed way, but native MapReduce has certain drawbacks including high communication and computation overhead. In this paper, the Map-Scan-Reduce process is divided into three steps: MAP, SCAN, and REDUCE, which solve the problems of native MapReduce. Users scheduling and data preprocessing is implemented using adaptive neuro fuzzy scheduler and improved version of M-Z-D-S (Max–Min, Z-score, and decimal scaling). Furthermore, clusters privacy is protected using differential privacy method and clusters quality is validated using two matrices such as Silhoutte and Dunn for inter-cluster and intra-cluster validations, respectively. Finally, we conduct experiments to analyze the performance of the proposed work in terms of clustering accuracy, speedup ratio (execution time), and efficiency (precision, adjusted Rand index, and normalized mutual information).

Achieving High Privacy Protection in Location-based Recommendation Systems

In recent years, privacy has become great attention in the research community. In Location-based Recommendation Systems (LbRSs), the user is constrained to build queries depend on his actual position to search for the closest points of interest (POIs). An external attacker can analyze the sent queries or track the actual position of the LbRS user to reveal his\her personal information. Consequently, ensuring high privacy protection (which is including location privacy and query privacy) is a fundamental thing. In this paper, we propose a model that guarantees high privacy protection for LbRS users. The model is work by three components: The first component (selector) uses a new location privacy protection approach, namely, the smart dummy selection (SDS) approach. The SDS approach generates a strong dummy position that has high resistance versus a semantic position attack. The second component (encryptor) uses an encryption-based approach that guarantees a high level of query privacy versus a sampling query attack. The last component (constructor) constructs the protected query that is sent to the LbRS server. Our proposed model is supported by a checkpoint technique to ensure a high availability quality attribute. Our proposed model yields competitive results compared to similar models under various privacy and performance metrics.

Privacy Preservation for Friend-Recommendation Applications

Friend-recommendation applications as one kind of typical social applications can satisfy the social contact needs of different users and become tools for developing a social relationship. However, the privacy leakage has turned into an insurmountable obstacle to the market success of such applications. Existing privacy protection approaches for social applications either introduce untrusted third parties or sacrifice information accuracy. As for friend-recommendation applications particularly, the multihop trust chain and anonymous message methods still have a defect that the hacker can act as a user to acquire information. In this paper, we put forward the privacy protection mechanism based on zero knowledge without any privacy leakage to the application server. In detail, the server knows nothing about the user’s information, but can still provide users with accurate information on friend recommendation. We also analyze the potential attack methods and propose the corresponding solution. Our simulation results verify the effectivity and efficiency of our scheme.

A Privacy Protection Model of Data Publication Based on Game Theory

With the rapid development of sensor acquisition technology, more and more data are collected, analyzed, and encapsulated into application services. However, most of applications are developed by untrusted third parties. Therefore, it has become an urgent problem to protect users’ privacy in data publication. Since the attacker may identify the user based on the combination of user’s quasi-identifiers and the fewer quasi-identifier fields result in a lower probability of privacy leaks, therefore, in this paper, we aim to investigate an optimal number of quasi-identifier fields under the constraint of trade-offs between service quality and privacy protection. We first propose modelling the service development process as a cooperative game between the data owner and consumers and employing the Stackelberg game model to determine the number of quasi-identifiers that are published to the data development organization. We then propose a way to identify when the new data should be learned, as well, a way to update the parameters involved in the model, so that the new strategy on quasi-identifier fields can be delivered. The experiment first analyses the validity of our proposed model and then compares it with the traditional privacy protection approach, and the experiment shows that the data loss of our model is less than that of the traditional k-anonymity especially when strong privacy protection is applied.

Fractal Intelligent Privacy Protection in Online Social Network Using Attribute-Based Encryption Schemes

While the online social network (OSN) has brought much convenience to users, there are still some serious problems, such as personal privacy leaks. Today, OSN security and privacy protection are one of the most important focuses of the research. In this paper, we present an intelligent privacy protection approach to solve problems of security and privacy protection in OSNs. First, the proposed algorithm combines a neural network with a hybrid hierarchy genetic algorithm and radial basis function, which is used to construct a prediction model of OSN security. Then, a support vector machine is applied to preprocess information of the OSN, and the attribute-based encryption scheme is adopted to encrypt the OSN information. Finally, a particle swarm optimization algorithm is used to improve OSN security and privacy protection. The experimental results demonstrate the effectiveness of the proposed method.

QLDS: A Novel Design Scheme for Trajectory Privacy Protection with Utility Guarantee in Participatory Sensing

Participatory sensing, leveraging on the ubiquity of cheap sensors in mobile devices, enables various promising applications of great social benefit. However, its ubiquitous sampling and openness results in serious privacy concerns. People's activity trajectories may reveal their private information such as home and work place and thus requires proper protection. In this paper, we propose a novel design scheme, called query logics detached storage (QLDS), for trajectory privacy protection. The core idea of QLDS is to extract the query logics for personal trajectory retrieval and make actual trajectory tuples not clustered to any route-identity or user-identity at server end, which introduces fine-granularity anonymity. The QLDS design scheme stores the extracted query logics at users own client devices and the un-clustered location tuples at the backend server, guaranteeing trajectory reconstruction at client-end and privacy preservation at server-end. Besides, integration of QLDS with other privacy protection approaches can further enhance the protection strength and bring flexible configurations to meet individuals’ variable privacy concerns. The theoretical analytics is provided for the privacy and utility evaluation. The data retrieval performance of QLDS is experimentally evaluated in real-world internet environment.

Enhancing social network privacy with accumulated non-zero prior knowledge

With the fast development of social networks, privacy protection on social network data has already attracted more and more research attention. If an adversary has collected enough information by intentionally querying a social network, the privacy of social network data might be successfully inferred based on the previous query results, which is seldom investigated by most existing approaches. In this paper, we first formulate the correlated query results as the non-zero prior knowledge, then propose a novel differential privacy approach to enhance privacy of social network data from being inferred. The corresponding ϵ-difference is re-formulated as well as the calculation of the sensitivity between two “neighboring” social graphs. Particularly, the calculation of sensitivity is proposed for three widely adopted queries on social networks, i.e., node degree distribution query, cut set query and the shortest path query. To evaluate our approach, rigorous experiments have been performed on three real world data sets. The promising experimental results have demonstrated that the proposed approach is superior to the state-of-the-art privacy protection approaches with respect to data privacy and data utility.

Cognitive Approach for Location Privacy Protection

While enjoying the convenience of location-based services (LBSs) in everyday life, wireless device users could also put their location privacy at risk. An untrusted LBS provider can store mobile users’ data on its server, track users in various ways or share users location data to the third parties. To protect LBS users’ privacy, many position confusion algorithms were proposed, but those algorithms often have difficulty balancing the utility-privacy tradeoffs. In this paper, we propose a new cognitive approach that enables near-complete privacy protection for LBS users by leveraging existing social network resources. We introduce a heterogeneous multi-server architecture that cuts off the direct connection between the LBS queries and the query issuers, and an auction-based incentive mechanism guaranteed user participation, which is critical for the success of the proposed architecture. A simulation system and a smartphone application were developed, and our evaluation results show that the proposed method can not only achieve the near-total privacy protection for LBS users, but also significantly improve the quality of the services.

Agent-Based System for Efficient kNN Query Processing with Comprehensive Privacy Protection

Recently, location based services (LBSs) have become increasingly popular due to advances in mobile devices and their positioning capabilities. In an LBS, the user sends a range of queries regarding his k-nearest neighbors (kNNs) that have common points of interests (POIs) based on his real geographic location. During the query sending, processing, and responding phases, private information may be collected by an attacker, either by tracking the real locations or by analyzing the sent queries. This compromises the privacy of the user and risks his/her safety in certain cases. Thus, the objective of this paper is to ensure comprehensive privacy protection, while also guaranteeing the efficiency of kNN query processing. Therefore, we propose an agent-based system for dealing with these issues. The system is managed by three software agents (selectorDL, fragmentorQ, and predictor). The selectorDL agent executes a Wise Dummy Selection Location (WDSL) algorithm to ensure the location privacy. The mission of the selectorDL agent is integrated with the mission of the fragmentorQ agent, which is to ensure the query privacy based on Left-Right Fragmentation (LRF) algorithm. To guarantee the efficiency of kNN processing, the predictor agent executes a prediction phase depending on a Cell Based Indexing (CBI) technique. Compared to similar privacy protection approaches, the proposed WDSL and LRF approaches showed higher resistance against location homogeneity attacks and query sampling attacks. In addition, the proposed CBI indexing technique obtains more accurate answers to kNN queries than the previous indexing techniques.

A Package Reduction Approach To Modeling and Analysis of Cross-Organization Emergency Response Processes With Privacy Protected

The emergency disposals are usually charged by several geographically dispersed and logically collaborated emergency organizations. In addition, each emergency organization owns its private emergency response process and can operate independently. In this case, modeling such cross-organizational emergency response processes is really a challenging issue when considering: 1) effective collaboration and coordination among different emergency partners; and 2) reasonable privacy and security protection mechanism to maintain the sensitive information confidential and unseen by other involved partners. In this paper, we propose a package reduction-based privacy protection approach to facilitate the modeling. Specifically, a kind of workflow nets extended with time, resource, and message factors, called TRM_WF_nets for short, is first introduced to model cross-organization emergency response processes. Then, a three-layered framework is proposed to model cross-organization emergency response processes by taking into account their privacy protection and temporal performance evaluation. Next, a set of reduction rules are proposed to reduce the scale of a TRM_WF_net while keeping its external observable timing, message, and resource factors invariant. These reduction rules not only improve the efficiency of temporal performance evaluation but also protect the business privacy of each emergency organization during its collaboration and interaction with others. Finally, a real-life scenario of cross-organization fire emergency response processes is used to validate our proposed approaches.