Graph Convolutional Networks for Privacy Metrics in Online Social Networks

Abstract

In recent years, privacy leakage events in large-scale social networks have become increasingly frequent. Traditional methods relying on operators have been unable to effectively curb this problem. Researchers must turn their attention to the privacy protection of users themselves. Privacy metrics are undoubtedly the most effective method. However, social networks have a substantial number of users and a complex network structure and feature set. Previous studies either considered a single aspect or measured multiple aspects separately and then artificially integrated them. The measurement procedures are complex and cannot effectively be integrated. To solve the above problems, we first propose using a deep neural network to measure the privacy status of social network users. Through a graph convolution network, we can easily and efficiently combine the user features and graph structure, determine the hidden relationships between these features, and obtain more accurate privacy scores. Given the restriction of the deep learning framework, which requires a large number of labelled samples, we incorporate a few-shot learning method, which greatly reduces the dependence on labelled data and human intervention. Our method is applicable to online social networks, such as Sina Weibo, Twitter, and Facebook, that can extract profile information, graph structure information of users' friends, and behavioural characteristics. The experiments show that our model can quickly and accurately obtain privacy scores in a whole network and eliminate traditional tedious numerical calculations and human intervention. the NetEase user database was leaked, and more than 100 million users' 163 and 126 mailbox information was leaked, including usernames, passwords, password security information, login IPs, and user birthdays. These privacy leakages may lead to a series of malicious acts [2-5], including but not limited to tracking, defamation, spam, phishing, identity theft, personal data cloning, Sybil attack, etc. However, academia has always focused on large-scale industrial networks, such as the Internet of Things, smart grids, and cloud storage networks, ignoring the privacy protection of individual users because the privacy leakage of large-scale networks causes substantial visible economic losses, but the impact of personal information leakage is scattered and small. Moreover, users' use of social networks is a process of sharing public information. Applying privacy protection methods to traditional industrial networks will damage user experience.The existing privacy protection methods in social networks include anonymity, decentralisation, encryption, information security regulations, fine-grained privacy settings and access control, and improving user privacy awareness and privacy behaviour [6]. The first four methods need to rely on operators, which has proven to be unreliable. With the rapid development of attribute inference, link inference, personal identification, and community discovery, the role of anonymisation is becom...

A Comprehensive Analysis of Privacy-Preserving Solutions Developed for Online Social Networks

“…We summarize and compare the famous AI-based G anonymization techniques used for PPGP in Table 6. [175] Technical Predicts the SI in a G using ML and suggests how to safeguard it NB, SVM, RF S Yin et al [176] Technical Strikes a balance between privacy and utility in distributing G k-means algorithm R Wang et al [177] Technical Privacy preservation of degree information in releasing G k-means algorithm R Ju et al [178] Technical Strong privacy of V in G along with higher accuracy and utility k-means algorithm R Zheng et al [179] Technical Strong privacy of V in G and fewer changes to G's structure GNN algorithm R Paul et al [180] Technical Preserves the structural properties of G in anonymization process k-means algorithm R Hoang et al [181] Technical Preserves the privacy of SN users modelled via knowledge of G k-ad algorithm R Hoang et al [182] Technical Preserves the privacy of SN users when G is subject to multiple releases CTKGA algorithm R Chen et al [183] Technical Privacy preservation of SN users when G contains outliers and categorical attributes DBSCAN clustering R Narula et al [184] Technical Privacy preservation of identity and emotion-related information in OSN data CNN algorithm R Zitouni et al [185] Technical Privacy preservation by concealing the identity in image data CNN and LSTM R Ahmed et al [186] Technical Privacy preservation by concealing the identity and other SI in images Neural Network R Matheswaran et al [187] Technical Privacy preservation of image data in retrieval and storage in clouds Watermarking R Li et al [188] Technical Both anonymity-and utility-preserving solutions for OSN data GAN Algorithm R Lu et al [189] Technical Privacy preservation by reducing the prediction accuracy of sensitive links in G VGAE and ARVGA R Li et al [190] Technical Privacy preservation using profile, graph structure, and behavioral information GCNN algorithm R Wanda et al [191] Technical Privacy preservation of vulnerable nodes in G using dynamic deep learning CNN architecture R Li et al [192] Technical Privacy preservation of users when a user's job/education-place changes with time Supervised ML R Bioglio et al [193] Technical Privacy preservation of contents in OSN platforms based on sensitivity analysis Deep NN R Hermansson et al [194] Technical Preserves better accuracy for data-mining and analytical tasks from G SVM algorithm R Kalunge et al [195] Technical Preserves better utility (path length and IL) ...…”

Anonymization Techniques for Privacy Preserving Data Publishing: A Comprehensive Survey

“…social network analysis (e.g., graph operations) in multi-party computation process/setting offered by SNs data, researches have turned their attention to devise new and realistic anonymization methods leveraging advanced artificial intelligence (AI) techniques. Li et al [228] designed a deep learning (DL) model that combines multiple factors such as attribute information, graph structure, and behaviour characteristics while avoiding tedious calculation procedures to measure the privacy in SNs. The proposed model considers the deep relationship between all three factors (user attributes information, graph structure, and behaviour characteristics) to accurately obtain the privacy score.…”

What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data

“…However, using FSL, it only requires each user to provide 3 to 7 login dialogues. In addition, LSL is also applied to the assessment of personal social privacy status [124]. The intervention of FSL dramatically reduces the dependence on labeled data and manual intervention.…”