Link-privacy preserving graph embedding data publication with adversarial learning

Zhang, Kainan; Tian, Zhi; Cai, Zhipeng; Seo, Daehee

doi:10.26599/tst.2021.9010015

Cited by 21 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models are highly probable: edge node unlinkability and weight unlinkability. In [43], the authors have developed a unique linkprivacy maintained graph embedding system based on adversarial learning. The proposed approach focuses on reducing the accuracy of adversary prediction for sensitive attributes while allowing nonsensitive attributes in graph embedding, such as graph topology and node properties.…”

Section: State-of-artmentioning

confidence: 99%

Enhanced Clustering Based OSN Privacy Preservation to Ensure k-Anonymity, t-Closeness, l-Diversity, and Balanced Privacy Utility

Gangarde¹,

Sharma²,

Pawar³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Online Social Networks (OSN) sites allow end-users to share a great deal of information, which may also contain sensitive information, that may be subject to commercial or non-commercial privacy attacks. As a result, guaranteeing various levels of privacy is critical while publishing data by OSNs. The clustering-based solutions proved an effective mechanism to achieve the privacy notions in OSNs. But fixed clustering limits the performance and scalability. Data utility degrades with increased privacy, so balancing the privacy utility trade-off is an open research issue. The research has proposed a novel privacy preservation model using the enhanced clustering mechanism to overcome this issue. The proposed model includes phases like pre-processing, enhanced clustering, and ensuring privacy preservation. The enhanced clustering algorithm is the second phase where authors modified the existing fixed k-means clustering using the threshold approach. The threshold value is determined based on the supplied OSN data of edges, nodes, and user attributes. Clusters are k-anonymized with multiple graph properties by a novel one-pass algorithm. After achieving the k-anonymity of clusters, optimization was performed to achieve all privacy models, such as k-anonymity, t-closeness, and l-diversity. The proposed privacy framework achieves privacy of all three network components, i.e., link, node, and user attributes, with improved utility. The authors compare the proposed technique to underlying methods using OSN Yelp and Facebook datasets. The proposed approach outperformed the underlying state of art methods for Degree of Anonymization, computational efficiency, and information loss.

show abstract

Section: State-of-artmentioning

confidence: 99%

Enhanced Clustering Based OSN Privacy Preservation to Ensure k-Anonymity, t-Closeness, l-Diversity, and Balanced Privacy Utility

Gangarde¹,

Sharma²,

Pawar³

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…How to secure the sensitive information contained in big data is a key to make full use of the value hidden in big data [31][32][33]. Hash technique is recruited in [34,35] to secure the personal information contained in user big data.…”

Section: Privacy-aware Data Utilizationmentioning

confidence: 99%

Private anomaly detection of student health conditions based on wearable sensors in mobile cloud computing

et al. 2022

View full text Add to dashboard Cite

With the continuous spread of COVID-19 virus, how to guarantee the healthy living of people especially the students who are of relative weak physique is becoming a key research issue of significant values. Specifically, precise recognition of the anomaly in student health conditions is beneficial to the quick discovery of potential patients. However, there are so many students in each school that the education managers cannot know about the health conditions of students in a real-time manner and accurately recognize the possible anomaly among students quickly. Fortunately, the quick development of mobile cloud computing technologies and wearable sensors has provided a promising way to monitor the real-time health conditions of students and find out the anomalies timely. However, two challenges are present in the above anomaly detection issue. First, the health data monitored by massive wearable sensors are often massive and updated frequently, which probably leads to high sensor-cloud transmission cost for anomaly detection. Second, the health data of students are often sensitive enough, which probably impedes the integration of health data in cloud environment even renders the health data-based anomaly detection infeasible. In view of these challenges, we propose a time-efficient and privacy-aware anomaly detection solution for students with wearable sensors in mobile cloud computing environment. At last, we validate the effectiveness and efficiency of our work via a set of simulated experiments.

show abstract

“…However, the network topology belongs to non-Euclidean data, that is, the number of neighbor nodes of each node in graph is not necessarily the same. To solve this problem, researchers have exquisitely designed a variant of CNN to extract features from non-Euclidean structured data, named GCN, which can operate directly on graphs 29 , 30 .…”

Section: Related Workmentioning

confidence: 99%

A link prediction method for MANETs based on fast spatio-temporal feature extraction and LSGANs

Shao

Wang

Liu

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Link prediction aims to learn meaningful features from networks to predict the possibility of topology. Most of the existing research on temporal link prediction is mainly aimed at networks with slow topology changes. They ignore the information of topology interval and link duration. This paper proposes a link prediction model named FastSTLSG. It can automatically analyze the features of the topology in a unified framework to effectively capture the spatio-temporal correlation of Mobile Ad Hoc Networks. First, we regard the changing topology as a chaotic system, transform it into a series of static snapshots based on the autocorrelation function; Next, the fast graph convolutional network efficiently analyses the topological relationships between nodes and reduces the computational complexity by importance sampling. Then, the gate recurrent unit captures the temporal correlation between snapshots. Finally, the fully connected layer reconstructs the topological structure. In addition, we take full advantage of least squares generative adversarial networks to further improve the performance of generator to obtain high-quality link prediction results. Extensive experiments on different datasets show that our FastSTLSG model obtains higher prediction accuracy compared with existing baseline models.

show abstract

Link-privacy preserving graph embedding data publication with adversarial learning

Cited by 21 publications

References 11 publications

Enhanced Clustering Based OSN Privacy Preservation to Ensure k-Anonymity, t-Closeness, l-Diversity, and Balanced Privacy Utility

Enhanced Clustering Based OSN Privacy Preservation to Ensure k-Anonymity, t-Closeness, l-Diversity, and Balanced Privacy Utility

Private anomaly detection of student health conditions based on wearable sensors in mobile cloud computing

A link prediction method for MANETs based on fast spatio-temporal feature extraction and LSGANs

Contact Info

Product

Resources

About