Research On The Strategy Of Sybil Attack Defense In Social Network

The emergence of social networks not only provides great convenience for individuals to communicate with each other but also facilitates the information dissemination.However,openness of the social environment,diversification of the social manners and centralized storage of information also inevitably allow malicious nodes to launch attacks then obtaining illegal benefits.Sybil attacker generates a large number of false sybils,sybils collude with each other to launch synergistically attack,which gives powerful support to some other aggressive behaviors of malicious nodes and greatly enhance the attack intensity.Sybil attack makes a seriously threat to the interests of social individuals and system security.In addition,pretending as normal nodes with high similarity and collaborating to avoid detection bring great difficulty to the recognition of sybils.Designing sybil detection mechanism with high accuracy then defending Sybil attack is urgent to protect social individual interests and system security.Firstly,the basic concepts and the key technologies of social networks are summaried.Then analyzing the security problems in social networks and explaining the necessity of detecting sybil attack in social networks.Furthermore,the existing strategies of Sybil attack defense with sybils detection in social networks are summarized.Secondly,basing on the analysis of the sybil's behaviors,a strategy of Sybil attack defense applied to social networks is proposed.Calculating the influence of nodes according to static similarity and dynamic similarity and then selecting the suspicious nodes based on the influence.Next,using the Hidden Markov Model(HMM)to infer the true identity of suspicious nodes by observing their abnormal behaviors,thus detecting the Sybil more precisely and defending Sybil attack effectively.Analysis results show that the proposed mechanism can effectively improve the recognition rate and reduce the false detection rate of the sybil and thereby protecting the privacy and interests of social individuals better.Thirdly,in order to further improve the accuracy,sensitivity and scalability of the sybils detection in strategy of Sybil attack defense,thesis proposes a Support Vector Machine(SVM)based sybil defense strategy applied to large scale social networks.A terminal-cloud coordination sybil detection system is designed to collect and process the behavior information of nodes in time.Next evaluating the activity,prestige and malicious degree of nodes to form the behavior characteristic vector on the basis of analyzing the difference of social behaviors between sybil and normal node.At last,we design the node classifier using Support Vector Machine to learn the node behavior information and then determining the node states to detect sybils.Numerical analysis shows that the proposed method can further improve the recognition rate and reduce the false detection rate of the sybil to have a more accurate and timely detection of Sybil and defend the Sybil attack more effectively.At the same time,it has better scalability and detection sensitivity.Finally,concluding the existing work and prospecting the future work.