![]() ![]() One of these tricks is sending spam emails in different languages beside users’ vernaculars. Despite the anti-spam technology development, spammers keep working hard to find new strategies which help deliver unwanted messages to email users all around the world. In recent years, the battle against spam e-mail is extremely fierce. The detecting achievement of multilingual rule was 89.5% for the true detection and only 3.8% for the failed alarm at the threshold of 2 while the true detection rate of single language rule was not over 61% and the failed alarm rate was up to 4.9%. The experiments were conducted against the dataset of three languages including Chinese, Vietnamese and English. The theoretical framework of generating and maintaining multilingual rules were also illustrated. ![]() ![]() In this paper, we introduced a statistical rule-based method to create rules for SpamAssassin to detect spams in different languages. 2 School of Engineering and IT, University of New South Wales, Canberra, Australia.1 Faculty of Information Technology, Hanoi University, Hanoi, Vietnam.Minh Tuan Vu 1, Quang Anh Tran 1, Frank Jiang 2 and Van Quan Tran 1 Journal of Machine to Machine Communications, Vol. # 2.Received 15 April 2013 Accepted Publication 4 August 2014 # are found together in the same message: # Headers that seem to only be used by a single spamming software and # X-Fix example: NTMail fixed non RFC822 compliant EMail message ![]() # header existence tests (description is added automatically) GAPPY_SUBJECT (_GAPPY_SUBJECT
0 Comments
Leave a Reply. |