- Title
- Trust-aware detection of malicious users in dating social networks
- Creator
- Shen, Xingfa; Lv, Wentao; Qiu, Jianhui; Kaur, Achhardeep; Xiao, Fengjun; Xia, Feng
- Date
- 2023
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/198704
- Identifier
- vital:19089
- Identifier
-
https://doi.org/10.1109/TCSS.2022.3174011
- Identifier
- ISSN:2329-924X (ISSN)
- Abstract
- Online dating is an increasingly thriving business which boosts billion-dollar revenues and attracts users in the tens of millions. Despite its popularity, internet dating is not exempt from the concerns about privacy and trust posed by the revelation of potentially sensitive data as well as the exposure to self-reported (and hence potentially distorted) information. The increasing popularity of online dating networks leads to an increase in security concerns and challenges, as well as harmful actions and attacks, such as creating fake accounts, phishing on these networks. To maintain the safety of legitimate online dating users, it is critical to recognize and isolate criminal people as soon as possible. However, researchers concerning malicious user detection in dating social networks are merely a few. To address some key challenges in this space, we propose a trust-aware detection framework to detect malicious users based on different kinds of data from a real dating site. In particular, we develop a user trust model to distinguish between malicious and legitimate users. Furthermore, we propose a novel data-balancing method to improve the recall rate of malicious user detection. Extensive experiments have been conducted over real-world datasets. The results show that the proposed approach yields a precision of up to 59.16% and a recall rate of up to 73%, which is significantly higher than other baseline algorithms. © 2014 IEEE.
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Relation
- IEEE Transactions on Computational Social Systems Vol. 10, no. 5 (2023), p. 2587-2598
- Rights
- All metadata describing materials held in, or linked to, the repository is freely available under a CC0 licence
- Rights
- Copyright @ 2022 IEEE
- Subject
- MD Multidisciplinary; Anomaly detection; Malicious users; Social networks; Trust; User behavior
- Reviewed
- Funder
- This work was supported by the National Natural Science Foundation of China under Grant 62072121.
- Hits: 166
- Visitors: 165
- Downloads: 0
Thumbnail | File | Description | Size | Format |
---|