GroupFound: An effective approach to detect suspicious accounts in online social networks
Online social networks are an important part of people’s life and also become the platform where spammers use suspicious accounts to spread malicious URLs. In order to detect suspicious accounts in online social networks, researchers make a lot of efforts. Most existing works mainly utilize machine...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi - SAGE Publishing
2017-07-01
|
Series: | International Journal of Distributed Sensor Networks |
Online Access: | https://doi.org/10.1177/1550147717722499 |
_version_ | 1797717481496772608 |
---|---|
author | Bo Feng Qiang Li Xiaowen Pan Jiahao Zhang Dong Guo |
author_facet | Bo Feng Qiang Li Xiaowen Pan Jiahao Zhang Dong Guo |
author_sort | Bo Feng |
collection | DOAJ |
description | Online social networks are an important part of people’s life and also become the platform where spammers use suspicious accounts to spread malicious URLs. In order to detect suspicious accounts in online social networks, researchers make a lot of efforts. Most existing works mainly utilize machine learning based on features. However, once the spammers disguise the key features, the detection method will soon fail. Besides, such methods are unable to cope with the variable and unknown features. The works based on graph mainly use the location and social relationship of spammers, and they need to build a huge social graph, which leads to much computing cost. Thus, it is necessary to propose a lightweight algorithm which is hard to be evaded. In this article, we propose a lightweight algorithm GroupFound , which focuses on the structure of the local graph. As the bi-followers come from different social communities, we divide all accounts into different groups and compute the average number of accounts for these groups . We evaluate GroupFound on Sina Weibo dataset and find an appropriate threshold to identify suspicious accounts. Experimental results have demonstrated that our algorithm can accomplish a high detection rate of 86 . 27 % at a low false positive rate of 8 . 54 % . |
first_indexed | 2024-03-12T08:37:57Z |
format | Article |
id | doaj.art-94aa25859d1b4c3f8263a6cf173cf7e6 |
institution | Directory Open Access Journal |
issn | 1550-1477 |
language | English |
last_indexed | 2024-03-12T08:37:57Z |
publishDate | 2017-07-01 |
publisher | Hindawi - SAGE Publishing |
record_format | Article |
series | International Journal of Distributed Sensor Networks |
spelling | doaj.art-94aa25859d1b4c3f8263a6cf173cf7e62023-09-02T17:09:19ZengHindawi - SAGE PublishingInternational Journal of Distributed Sensor Networks1550-14772017-07-011310.1177/1550147717722499GroupFound: An effective approach to detect suspicious accounts in online social networksBo Feng0Qiang Li1Xiaowen Pan2Jiahao Zhang3Dong Guo4Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, ChinaKey Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, ChinaOnline social networks are an important part of people’s life and also become the platform where spammers use suspicious accounts to spread malicious URLs. In order to detect suspicious accounts in online social networks, researchers make a lot of efforts. Most existing works mainly utilize machine learning based on features. However, once the spammers disguise the key features, the detection method will soon fail. Besides, such methods are unable to cope with the variable and unknown features. The works based on graph mainly use the location and social relationship of spammers, and they need to build a huge social graph, which leads to much computing cost. Thus, it is necessary to propose a lightweight algorithm which is hard to be evaded. In this article, we propose a lightweight algorithm GroupFound , which focuses on the structure of the local graph. As the bi-followers come from different social communities, we divide all accounts into different groups and compute the average number of accounts for these groups . We evaluate GroupFound on Sina Weibo dataset and find an appropriate threshold to identify suspicious accounts. Experimental results have demonstrated that our algorithm can accomplish a high detection rate of 86 . 27 % at a low false positive rate of 8 . 54 % .https://doi.org/10.1177/1550147717722499 |
spellingShingle | Bo Feng Qiang Li Xiaowen Pan Jiahao Zhang Dong Guo GroupFound: An effective approach to detect suspicious accounts in online social networks International Journal of Distributed Sensor Networks |
title | GroupFound: An effective approach to detect suspicious accounts in online social networks |
title_full | GroupFound: An effective approach to detect suspicious accounts in online social networks |
title_fullStr | GroupFound: An effective approach to detect suspicious accounts in online social networks |
title_full_unstemmed | GroupFound: An effective approach to detect suspicious accounts in online social networks |
title_short | GroupFound: An effective approach to detect suspicious accounts in online social networks |
title_sort | groupfound an effective approach to detect suspicious accounts in online social networks |
url | https://doi.org/10.1177/1550147717722499 |
work_keys_str_mv | AT bofeng groupfoundaneffectiveapproachtodetectsuspiciousaccountsinonlinesocialnetworks AT qiangli groupfoundaneffectiveapproachtodetectsuspiciousaccountsinonlinesocialnetworks AT xiaowenpan groupfoundaneffectiveapproachtodetectsuspiciousaccountsinonlinesocialnetworks AT jiahaozhang groupfoundaneffectiveapproachtodetectsuspiciousaccountsinonlinesocialnetworks AT dongguo groupfoundaneffectiveapproachtodetectsuspiciousaccountsinonlinesocialnetworks |