Detecting Malicious Accounts in Online Developer Communities Using Deep Learning

Qingyuan Gong, Jiayun Zhang, Yang Chen, Qi Li, Yu Xiao, Xin Wang, Pan Hui

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

1 Citation (Scopus)
91 Downloads (Pure)

Abstract

Online developer communities like GitHub provide services such as distributed version control and task management, which allow a massive number of developers to collaborate online. However, the openness of the communities makes themselves vulnerable to different types of malicious attacks, since the attackers can easily join and interact with legitimate users. In this work, we formulate the malicious account detection problem in online developer communities, and propose GitSec, a deep learning-based solution to detect malicious accounts. GitSec distinguishes malicious accounts from legitimate ones based on the account profiles as well as dynamic activity characteristics. On one hand, GitSec makes use of users' descriptive features from the profiles. On the other hand, GitSec processes users' dynamic behavioral data by constructing two user activity sequences and applying a parallel neural network design to deal with each of them, respectively. An attention mechanism is used to integrate the information generated by the parallel neural networks. The final judgement is made by a decision maker implemented by a supervised machine learning-based classifier. Based on the real-world data of GitHub users, our extensive evaluations show that GitSec is an accurate detection system, with an F1-score of 0.922 and an AUC value of 0.940.
Original languageEnglish
Title of host publicationCIKM '19:Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PublisherACM
Pages1251-1260
ISBN (Electronic)978-1-4503-6976-3
DOIs
Publication statusPublished - Nov 2019
MoE publication typeA4 Article in a conference publication
EventACM International Conference on Information & Knowledge Management - Beijing, Beijing, China
Duration: 3 Nov 20197 Nov 2019
Conference number: 28
http://www.cikm2019.net/

Publication series

NameACM International Conference on Information & Knowledge Management
ISSN (Print)2155-0751

Conference

ConferenceACM International Conference on Information & Knowledge Management
Abbreviated titleCIKM
CountryChina
CityBeijing
Period03/11/201907/11/2019
Internet address

Keywords

  • security and privacy protection
  • online social network
  • Deep Learning

Fingerprint Dive into the research topics of 'Detecting Malicious Accounts in Online Developer Communities Using Deep Learning'. Together they form a unique fingerprint.

  • Yang Chen

    Yu Xiao (Host)

    27 Aug 20187 Sep 2018

    Activity: Hosting a visitor typesHosting a visitor

Cite this