Abstract: File pollution is a common problem in P2P file sharing system.The similarity of biological immune system and P2P network is used to propose a suppression scheme for file pollution.Based on the immunity，an improved method of nodes similarity calculation and neighbor nodes selection is designed.It reduces the computation cost and improves the system performance.Simulation results show that the algorithm has high accuracy recognition and can suppress the spread of pollution file with lower communication costs.

Key words: peer to peer（P2P）, file pollution, file share

摘要： 文件污染是对等网络中存在的普遍问题。借鉴对等网络和生物免疫系统的相似性，提出一种基于免疫学习的文件污染抑制方案。基于免疫思想，设计了一种改进的节点相似度计算方法和邻居节点选择方案，减少了计算量，提高了系统性能。仿真实验表明，算法识别污染文件的精度较高，可以有效抑制污染文件的传播，并且通信开销较小。

关键词: 对等网络, 文件污染, 文件共享