Inferring Private Attributes Based on Graph Convolutional Neural Network in Social Networks

Tian, Yupan; Niu, Yang; Yan, Jun; Tian, Feng

doi:10.1109/nana.2019.00041

Cited by 7 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent methods use neural networks to represent nodes in low-dimensional vectors. [38] introduces graph-based convolutional neural networks to infer social media users' attributes. Their method leverage visible userprofiles and social links to predict target users missing attributes.…”

Section: Graph Based Methodsmentioning

confidence: 99%

Inferring attributes with picture metadata embeddings

Pijani

Imine

Rusinowitch

2020

SIGAPP Appl. Comput. Rev.

View full text Add to dashboard Cite

Users in online social networks are vulnerable to attribute inference attacks due to some published data. Thus, the picture owner's gender has a strong influence on individuals' emotional reactions to the photo. In this work, we present a graph-embedding approach for gender inference attacks based on pictures meta-data such as (i) alt-texts generated by Facebook to describe the content of images, and (ii) Emojis/Emoticons posted by friends, friends of friends or regular users as a reaction to the picture. Specifically, we apply a semi-supervised technique, node2vec, for learning a mapping of pictures meta-data to a low-dimensional vector space. Next, we study in this vector space the gender closeness of users who published similar photos and/or received similar reactions. We leverage this image sharing and reaction mode of Facebook users to derive an efficient and accurate technique for user gender inference. Experimental results show that privacy attack often succeeds even when other information than pictures published by their owners is either hidden or unavailable.

show abstract

Section: Graph Based Methodsmentioning

confidence: 99%

Inferring attributes with picture metadata embeddings

Pijani

Imine

Rusinowitch

2020

SIGAPP Appl. Comput. Rev.

View full text Add to dashboard Cite

show abstract

“…B Mei et al proposed a framework of attribute inference attack based on image and attribute, which integrates fast R-CNN face detection, CNN age classifier, and FCNN age classifier to predict the user's age attribute by detecting images in social networks [51]. Y Tian et al proposed a private attribute inference method based on a graph convolutional neural network, which used visible user-profiles and social links to predict the missing attributes of target users [52].…”

Section: E Othersmentioning

confidence: 99%

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Piao

Cui

2021

IEEE Access

View full text Add to dashboard Cite

With the rapid development of social networks, users pay more and more attention to the protection of personal information. However, the transmission of users' personal information through social networks will inevitably lead to privacy leakage and make users attacked. A large amount of privacy information can be inferred from the content and social traces published by users, which leads to the rise of privacy inference technology for users in social networks. Social relationship inference and attribute inference are two basic attacks on users' privacy in social networks. This is the first systematic review of privacy inference attacks in social networks. The purpose of this retrospective study is to provide a global summary, summarizing the time trend of the topic, and show the evolution of the topic in the past 15 years. In addition, this paper discusses the trend and development of this topic and finally looks forward to future work. The contribution of our work is helpful for researchers to continue their research in this field.

show abstract

“…There have been many studies about privacy inference attacks in OSNs with some being about user attribute inference 1,7,8,[11][12][13] while some others being about social relationship inference. 6,[14][15][16] Although the data used in those methods are based both on the attributes released by users and on relationships among users, the goals of those methods are different.…”

Section: Related Workmentioning

confidence: 99%

“…8 In AttriInfer, the pairwise Markov Random Field (pMRF) is used to model the structural information and the prediction results are computed by Loopy Belief Propagation (LBP). Tian et al used graph convolutional neural network (GCNN) to infer user's private attributes 11 in which privacy inference is treated as a classification problem and visible user profiles and social links are leveraged to predict the hidden attribute about the target user. Gong et al proposed a social-behavior-attribute (SBA) network model that considers the released attributes and social links as well as the behaviors of users 1 in which a method named vote distribution attack is designed under the SBA network model to perform attribute inference.…”

Section: Related Workmentioning

confidence: 99%

Social influence‐based privacy inference attacks in online social networks

Zhu

et al. 2021

Security and Privacy

View full text Add to dashboard Cite

Privacy inference attacks in online social networks aim at inferring hidden attributes of target users based on released attributes of the users as well as information about social relationships in the networks. Although many privacy inference methods have been proposed in recent years, most of the methods have mostly focused on pursuing high accuracy of the inference results without paying too much attention on identifying users who make the most contributions to the inference, making it less useful in the development of effective countermeasures. In this paper, by taking full consideration of the roles of users in privacy inference, we propose a privacy inference method based on graph attention networks that can provide information about not only the private attributes of the target users, but also the importance of the users in the process of inferring the results. We also design a novel mechanism for the selection of influential users to make our proposed method adaptive to the characteristics of user influence diffusion, resulting in involving fewer number of users in privacy inference and hence improving the efficiency. We also performed some experiment to evaluate the proposed method using a real online social network dataset to show the effectiveness of the proposed method. Comparison with other comparable methods also shows that the results of our proposed method are more accurate.

show abstract

Inferring Private Attributes Based on Graph Convolutional Neural Network in Social Networks

Cited by 7 publications

References 7 publications

Inferring attributes with picture metadata embeddings

Inferring attributes with picture metadata embeddings

Privacy Inference Attack Against Users in Online Social Networks: A Literature Review

Social influence‐based privacy inference attacks in online social networks

Contact Info

Product

Resources

About