Cost-effective spam detection in p2p file-sharing systems

Spam is highly pervasive in P2P file-sharing systems and is difficult to detect automatically before actually downloading a file due to the insufficient and biased description of a file returned to a client as a query result. To alleviate this problem, we propose probing technique to collect more complete feature information of query results from the network and apply feature-based ranking for automatically detecting spam in P2P query result sets. Furthermore, we examine the tradeoff between the spam detection performance and the network cost. Different ways of probing are explored to reduce the network cost. Experimental results show that the proposed techniques successfully decrease the amount of spam by 9% in the top200 results and by 92% in the top-20 results with reasonable cost. Categories and Subject Descriptors H.3.3 [Information Storage and Retrieval]: Information Search and Retrieval – Search Process General Terms Measurement, Experimentation, Security Keywords P2P search,...

• Type: Conference
• Year: 2008
• Where: CIKM
• Authors: Dongmei Jia
• Keywords: CIKM 2008, Information Technology, Network Cost, P2P File-sharing Systems, Spam Detection Performance