Article
Engineering, Electrical & Electronic
Vijay Kumar Yadav, Nitish Andola, Shekhar Verma, S. Venkatesan
Summary: This article proposes an anonymous linkable location-based services (AL2BS) scheme using linkable ring signcryption technique, which provides protection for vehicle user's query privacy and LBS server's data privacy without revealing the user's identity. The efficiency of the AL2BS scheme is independent of the size of the LBS server's database.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Long Li, Jianbo Huang, Liang Chang, Jian Weng, Jia Chen, Jingjing Li
Summary: With the widespread use of smartphones with embedded positioning systems and digital maps, location-based services (LBSs) have become popular and convenient in people's daily lives, but concerns about privacy leakage have emerged. To address this issue, a dual privacy-preserving scheme (DPPS) is proposed, which includes a correlation model based on a hidden Markov model (HMM) to prevent privacy disclosure caused by location correlations, and an advanced k-anonymity algorithm to provide query probability anonymity for each single location by constructing cloaking regions with realistic and indistinguishable dummy locations. The effectiveness and efficiency of DPPS are validated through theoretical analysis and experimental verification using a real-life dataset.
FRONTIERS OF COMPUTER SCIENCE
(2023)
Article
Engineering, Civil
Vijay Kumar Yadav, Shekhar Verma, Subramanian Venkatesan
Summary: User and point of interest (POI) privacy are major concerns in location-based services (LBS). Current schemes either protect query content or location privacy. The proposed L2BSWOT scheme reduces communication and computation costs while meeting all privacy requirements in LBS.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Information Systems
Vijay Kumar Yadav, Nitish Andola, Shekhar Verma, S. Venkatesan
Summary: A privacy-provisioning location-based service (P2LBS) scheme is proposed to protect the privacy of user queries and services provided by the server, while also offering anonymous payment. The scheme utilizes ring signatures for user authentication and an anonymous payment protocol for server authentication. Query privacy and services' reply privacy are ensured through an oblivious transfer protocol. Results demonstrate that the P2LBS scheme is more efficient in terms of communication and computation costs compared to other current state-of-the-art schemes, fulfilling all the necessary requirements for a viable LBS scheme.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Information Systems
Sina Shaham, Ming Ding, Bo Liu, Shuping Dang, Zihuai Lin, Jun Li
Summary: In recent years, there has been a growing demand for location-based services in daily life, leading to concerns about user location privacy. To address this, researchers have developed dummy-based algorithms to protect user privacy. This paper introduces a new attack model and evaluation metric, followed by the development of a robust defense algorithm against the attack.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2021)
Article
Computer Science, Information Systems
Shiwen Zhang, Biao Hu, Wei Liang, Kuan-Ching Li, Brij B. Gupta
Summary: This article proposes a caching-based dual K-anonymous (CDKA) location privacy-preserving scheme in edge computing environments. The scheme uses an edge server to protect user location privacy by reducing device load and providing dual anonymity. Through security analysis and performance evaluation, the robustness and relatively low communication cost of the scheme are demonstrated.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Hardware & Architecture
Vijay Kumar Yadav, Nitish Andola, Shekhar Verma, S. Venkatesan
Summary: The privacy of user queries and LBS server services is a challenging issue, and existing schemes suffer from low efficiency and privacy concerns. We propose an efficient privacy-preserving scheme for location-based services (EP2LBS) using a lattice-based oblivious transfer protocol. The EP2LBS scheme effectively protects the privacy of user queries and LBS server services, and requires lower communication and computation costs compared to current state-of-the-art schemes.
JOURNAL OF SUPERCOMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Lei Wu, Xia Wei, Lingzhen Meng, Shengnan Zhao, Hao Wang
Summary: The study proposed a traffic density monitoring system that protects the location privacy of vehicles and the query privacy of users by adding a pseudonym server and a location anonymisation server, improving anonymity success rate and location privacy security.
CONNECTION SCIENCE
(2022)
Article
Chemistry, Analytical
Zhiping Xu, Jing Zhang, Pei-wei Tsai, Liwei Lin, Chao Zhuo
Summary: The paper discusses the importance of protecting user trajectory privacy and proposes an SM-based trajectory privacy-preserving algorithm, MTPPA, which successfully reduces the probability of privacy disclosure.
Article
Computer Science, Theory & Methods
Shaobo Zhang, Tao Guo, Qin Liu, Entao Luo, Kim-Kwang Raymond Choo, Guojun Wang
Summary: This paper proposes an accuracy-aware location privacy service, named ALPS, based on assisted regions to protect user location privacy while ensuring the accuracy of services. Two novel mechanisms (assisted regions mechanism and query obfuscation mechanism) are devised to protect user location privacy and ensure the accuracy of LSSs based on trilateration. Theoretical analysis and experimental evaluation demonstrate that our scheme can protect location privacy without compromising the accuracy of LSSs.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Osman Abul, Ozan Berk Bitirgen
Summary: This work explores location-privacy preserving location updates in data-centric people mobility applications by annotating an urban area with city networks and utilizing concepts like weak location k-anonymity and strong location k-anonymity to enhance location anonymity. Algorithms are used to test anonymity violations and selectively block requests in the online stage, with a focus on privacy/utility trade-offs addressed through extensive experimental evaluation.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Article
Computer Science, Theory & Methods
Hongbo Jiang, Jie Li, Ping Zhao, Fanzi Zeng, Zhu Xiao, Arun Iyengar
Summary: Location-based services bring convenience but also lead to privacy concerns. Existing studies categorize and review privacy-preserving techniques, summarizing their principles and advancements. This provides new research opportunities in the field.
ACM COMPUTING SURVEYS
(2021)
Article
Computer Science, Information Systems
Yanbing Ren, Xinghua Li, Yinbin Miao, Robert H. Deng, Jian Weng, Siqi Ma, Jianfeng Ma
Summary: Location-Based Services (LBSs) are widely used mobile applications, but the privacy of location information is a concern. Geo-Ind is a privacy protection model that provides security guarantees but disrupts statistical location distribution. To address this, we propose DistPreserv definition and a privacy-preserving LBS scheme that includes location perturbation and retrieval area determination methods. The proposed mechanism achieves DistPreserv and incentive compatibility, improving availability of location distributions by over 90% in experiments.
IEEE TRANSACTIONS ON MOBILE COMPUTING
(2023)
Article
Chemistry, Multidisciplinary
Jong Wook Kim
Summary: With the increasing demand for data sharing among various parties, it is more desirable to integrate data anonymization functionality into existing systems that can support online query processing.
APPLIED SCIENCES-BASEL
(2021)
Article
Computer Science, Theory & Methods
Yinbin Miao, Yutao Yang, Xinghua Li, Zhiquan Liu, Hongwei Li, Kim-Kwang Raymond Choo, Robert H. H. Deng
Summary: With the rapid development of Location-Based Services (LBS), the security issues such as location privacy leakage have become a concern. In this study, an efficient Privacy-preserving Spatial Range Query (PSRQ) scheme is proposed by combining Geohash algorithm with Circular Shift and Coalesce Bloom Filter (CSC-BF) framework and Symmetric-key Hidden Vector Encryption (SHVE). Additionally, a Confused Bloom Filter (CBF) is designed to confuse the inclusion relationship in Bloom filter, and a more secure and practical enhanced scheme PSRQ+ is proposed. The experimental results show significant improvement in query efficiency compared with previous solutions.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Editorial Material
Computer Science, Hardware & Architecture
Cyrus Shahabi
COMMUNICATIONS OF THE ACM
(2020)
Editorial Material
Computer Science, Artificial Intelligence
Kai Zheng, Yong Li, Cyrus Shahabi, Hongzhi Yin
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)
Editorial Material
Computer Science, Artificial Intelligence
Kai Zheng, Yong Li, Cyrus Shahabi, Hongzhi Yin
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Libin Zheng, Lei Chen, Cyrus Shahabi
Summary: Bike-sharing systems have become popular due to the development of mobile networks, however, not much attention has been paid to routing algorithms for shared-bike riders. This paper studies the routing problem for multiple shared-bike riders and proposes two heuristics to allocate limited resources among competing riders. The experiments show that the greedy-based routing algorithm is effective and efficient.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Tian Xie, Chaoyang He, Xiang Ren, Cyrus Shahabi, C. -C. Jay Kuo
Summary: This work proposes a layerwise-trained bipartite graph neural network (L-BGNN) embedding method for e-commerce applications, such as recommendation, classification, and link prediction. The method utilizes customized interdomain message passing and intradomain alignment operations to aggregate information in the bipartite graph, and employs a layerwise training algorithm to capture multihop relationships and improve training efficiency.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Proceedings Paper
Computer Science, Information Systems
Abbas Zaidi, Ritesh Ahuja, Cyrus Shahabi
Summary: Accurately monitoring the number of individuals inside a building is crucial in controlling COVID-19 transmission. Due to privacy concerns, the low adoption of contact tracing apps has led to the prevalence of passive digital tracking alternatives. The use of large arrays of WiFi access points makes it convenient to track mobile devices on university and industry campuses. However, there is still a risk of violating individual location privacy even with aggregate occupancy statistics. This study examines the use of Differential Privacy in reporting statistics and proposes discretization schemes to minimize the risk to individual users' privacy.
2022 23RD IEEE INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
George Constantinou, Cyrus Shahabi, Seon Ho Kim
Summary: The paper presents alternative methods to automatically place various models on a diverse set of edge devices, considering the geospatial coverage of video data, resource capabilities of edge devices, and the characteristics of the trained models.
2021 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA)
(2021)
Proceedings Paper
Computer Science, Information Systems
Luciano Nocera, George Constantinou, Luan Tran, Seon Ho Kim, Gabriel Kahn, Cyrus Shahabi
Summary: Generating hyper-local news at scale is challenging due to lack of available data and automated tools. Crosstown Foundry is a novel data-driven system that leverages a massive multi-modal dataset to generate personalized newsletters for readers in Los Angeles County.
SIGMOD '21: PROCEEDINGS OF THE 2021 INTERNATIONAL CONFERENCE ON MANAGEMENT OF DATA
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiao Sun, Mingxuan Yue, Zongyu Lin, Xiaochen Yang, Luciano Nocera, Gabriel Kahn, Cyrus Shahabi
Summary: Crime prediction using deep learning frameworks can improve resource allocation efficiency, with the proposed CrimeForecaster achieving better performance in capturing temporal and spatial dependencies. The research team also released a ten-year crime dataset for future use in Los Angeles.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE AND DEMO TRACK, ECML PKDD 2020, PT V
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Mingxuan Yue, Tianshu Sun, Fan Wu, Lixia Wu, Yinghui Xu, Cyrus Shahabi
Summary: This paper proposes a novel representation learning framework to obtain a unified representation of Areas of Interest from both contextual data and topological data, and the effectiveness of the model is confirmed through experiments with real-world package delivery data on ETA prediction.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: APPLIED DATA SCIENCE TRACK, ECML PKDD 2020, PT IV
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Mingxuan Yue, Yao-Yi Chiang, Cyrus Shahabi
Summary: A variational approach named VAMBC is proposed for clustering context sequences while simultaneously learning self-supervision and cluster assignments in a single phase to infer moving behaviors from context transitions in trajectories. Experiments show that VAMBC significantly outperforms state-of-the-art approaches in robustness and accuracy of clustering mobility behaviors in trajectories.
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2021: APPLIED DATA SCIENCE TRACK, PT IV
(2021)
Proceedings Paper
Computer Science, Information Systems
Sepanta Zeighami, Gabriel Ghinita, Cyrus Shahabi
Summary: Research recognizes the importance of secure skyline computation, but existing solutions have several shortcomings, such as high costs and reliance on assumptions like the presence of multiple non-colluding parties. A secure and efficient way to compute skylines is through result materialization, but this is more challenging for skyline queries due to large space requirements. Materialization reduces the response time of skyline queries from hours to seconds in the encrypted setting, with experiments showing improved performance and minimal data leakage.
2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2021)
(2021)
Proceedings Paper
Computer Science, Information Systems
George Constantinou, Onur Orhan, Roopal Kondepudi, Hyunjae Cho, Seon Ho Kim, Abdullah Alfarrarjeh, Cyrus Shahabi
Summary: The study explores image learning applications with massive visual data and introduces a new strategy called spatial crowd-based learning. Using FloraVision as an example, the integration of ML, crowdsourcing, and EC technologies for automated plant detection and mapping is demonstrated. By iteratively improving models and visualizing real-time query results, FloraVision provides convenient services for users.
2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2021)
(2021)
Proceedings Paper
Computer Science, Information Systems
Yanan Da, Ritesh Ahuja, Li Xiong, Cyrus Shahabi
Summary: Contact tracing is essential in controlling epidemic outbreaks like COVID-19, and systems like REACT can enhance privacy-enabled tracking for real-time monitoring. It helps trace contacts and monitor individual risks while allowing users to control data precision.
2021 IEEE 37TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2021)
(2021)
Article
Computer Science, Artificial Intelligence
Dingxiong Deng, Fan Bai, Yiqi Tang, Shuigeng Zhou, Cyrus Shahabi, Linhong Zhu
Summary: This paper studies label propagation in heterogeneous graphs under heterophily assumption for the first time, proposing a K-partite label propagation model to handle the combination of heterogeneous nodes/relations and heterophily propagation. The novel label inference algorithm framework with update rules in near-linear time complexity and incremental approach for updates have been verified for effectiveness and efficiency through extensive experiments on real datasets, showing superiority over existing label propagation methods.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2021)