It is very important to recognize and filter the spam short messages(SMS).As the contents and formats of spam messages are diverse,the ordinary filtering methods based on keyword matching and sending speed can not tackle this problem effectively.This paper first presents a formalized representation of the SMS network.On the basis of real short message samples,the social characteristics of the SMS network are analyzed and studied.Further analysis and statistical work are carried out to discover the un-normal patterns of spam senders in SMS network.An N-degree association spam filter algorithm(NASFA)based on the un-normal patterns of spam senders is presented.Experiments and analysis show that the algorithm can effciently recognize spam senders,and the wrong recognition rate is reduced significantly.
[1]
Albert,et al.
Emergence of scaling in random networks
,
1999,
Science.
[2]
Panos Argyrakis,et al.
Distribution of infected mass in disease spreading in scale-free networks
,
2003,
cond-mat/0301322.
[3]
Edsger W. Dijkstra,et al.
A note on two problems in connexion with graphs
,
1959,
Numerische Mathematik.
[4]
D. Sornette,et al.
Stretched exponential distributions in nature and economy: “fat tails” with characteristic scales
,
1998,
cond-mat/9801293.
[5]
Albert-László Barabási,et al.
Statistical mechanics of complex networks
,
2001,
ArXiv.