Abstract: On the basis of analyzing these days spam filtering techniques，this paper proposes an identifying technology of spam sending behavior based on P2P（ITSSB） according to the sending behavior of spam.An Anti-Spam P2P network is structured between email servers to save and share information about suspicion email.Spam is identified collaboratively according to information about suspicion email in the Anti-Spam P2P network.The experiment result shows the ITSSB is just for the character of sending mails together without depending on the email content，the language type and the format analysis.The ITSSB can be also applied to filtering a large number of spam in the process of MTA communication，speeding up the process，improving the accuracy and saving a lot of systematical resources，and having well filtering capability.

Key words: peer-to-peer network, JXTA, spam, bulk sending behavior

摘要： 在分析目前垃圾邮件过滤技术的基础上，并根据垃圾邮件大量发送行为特征，提出了一种基于P2P协作的垃圾邮件发送行为识别技术。该技术将各邮件服务器组成一个反垃圾邮件（Anti-Spam）P2P网络，每个邮件服务器储存可疑邮件信息并将这些信息共享在Anti-Spam P2P网络上，然后根据可疑邮件信息在Anti-Spam P2P网络上进行协作识别垃圾邮件。实验结果表明，该技术是针对垃圾邮件的群发特征而不依赖于邮件内容、语言类型或格式分析，在MTA阶段就能过滤大量垃圾邮件，提高了处理速度和准确率并节省大量的系统资源，具有良好的过滤性能。

关键词: P2P, JXTA, 垃圾邮件, 群发行为