Dynamic reputation information propagation based malicious account detection in OSNs
- PDF / 1,637,849 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 119 Downloads / 217 Views
(0123456789().,-volV)(0123456789(). ,- volV)
Dynamic reputation information propagation based malicious account detection in OSNs Haoyan Liang1 • Zhigang Chen2 • Jia Wu2
Ó Springer Science+Business Media, LLC, part of Springer Nature 2018
Abstract People all around the world have become increasingly dependent on online social networks (OSNs), meanwhile, the number of malicious accounts in OSNs is also rapidly growing. Traditional content-based data mining techniques and user graph-based methods are asking for more and more computing resources from networks providers, especially for the networks with huge and complicated network topologies. Moreover, traditional content-based analysis methods need to keep up with the times, which need to be retrained when the structure of users’ data changes or when the malicious contents come along with some pop cultures. With the purpose of reducing the dependence on network providers’ computing resources and improving the precision of detection, a novel detection method of malicious account, which bases on dynamic users’ reputation information propagation, is proposed in this paper. According to the comparison result of requesting user’s comprehensive reputation and malicious threshold, user can mark requesting user’s reputation so as to achieve the purpose of malicious account detection and providing indirect recommended reputation information about requesting user for other users. Through experiments with two real-world datasets and comparison with two typical efficient detection algorithms, this algorithm can effectively detect malicious accounts without the central detection system as well as improve the detection precision. Keywords Dynamic reputation information Online social networks Malicious account detection Trust relationship User interaction List of symbols Rig Reputation of user g recorded by user i Direct reputation vector of user g VigD I Indirect reputation vector of user g Vig rij g Variance of user g’s recommend reputation sent by user j ri g Variance threshold of recommend reputation of user g STi g Set of recommend information on user g during period T
& Zhigang Chen [email protected] & Jia Wu [email protected] 1
School of Information Science and Engineering, Central South University, Changsha 410083, China
2
School of Software, Central South University, Changsha 410075, China
aD ij bD ij tD ij dr MijD MijI MijC NijD NijI NijC UijD UijI UijC Pm xD xI
Counter of user j’s malicious recommend information Counter of user j’s real recommend information Counter of user j’s uncertain recommend information Threshold of recommend information that can be aggregated Direct malicious factor Indirect malicious factor Comprehensive malicious factor Direct normal factor Indirect normal factor Comprehensive normal factor Direct uncertain factor Indirect uncertain factor Comprehensive uncertain factor Proportion of malicious users Weight factor of direct observable information Weight factor of indirect observable information
123
Wireless Networks
c j dm Mh H
Data Loading...
