Link prediction for heterogeneous information networks based on enhanced meta-path aggregation and attention mechanism

Shao, Hao; Wang, Lunwen; Zhu, Rangang

doi:10.1007/s13042-023-01822-9

Cited by 5 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For social networks, such information contained in a link between two individuals may be diverse, such as kinship, partnership or communication relationship. As more and more personal information is easily accessible by others online, the problem of privacy leakage is getting worse [2]. These sensitive relationships that expose privacy are undesirable to be public, which may also lead to the disclosure of other information, such as identity and attributes.…”

Section: Introductionmentioning

confidence: 99%

Target Link Protection against Link-Prediction-Based Attacks via Artificial Bee Colony Algorithm Based on Random Walk

Jiang,

Liu,

et al. 2023

Preprint

View full text Add to dashboard Cite

Link prediction is a network analysis model used to discover missing links or future relationships that may appear, which has been widely used in many real network systems to predict the potential relationship between two individuals. However, link prediction can also be used by attackers to identify sensitive links that users are unwilling to expose, which makes only removing sensitive links from the original network ineffective and leads to the disclosure of privacy. In this paper, we propose a target link protection mechanism via artificial bee colony algorithm based on random walk (RABC), which can defend the link prediction attacks based on Resource Allocation (RA) metric effectively.To enhance the local search ability of RABC, the random walk algorithm is combined with the original artificial bee colony algorithm. Then, we compare our method with other existing methods, which shows that RABC has higher efficiency while ensuring the effectiveness. Finally, extensive experiments on real social networks are conducted to demonstrate the good performance of RABC on protecting sensitive links from being detected successfully by link prediction model. Furthermore, the perturbed networks generated by RABC is transferable to defend against other link prediction attacks.

show abstract

Section: Introductionmentioning

confidence: 99%