PeerShark: flow-clustering and conversation-generation for malicious peer-to-peer traffic identification

EURASIP Journal on Information Security

Table 1 Dataset details

Name	Number of flows	Number of conversations	Purpose
eMule	413,995	293,704	Train/Test
uTorrent	1,409,291	458,624	Train/Test
Vuze	1,207,963	603,145	Train/Test
Frostwire	890,300	234,335	Train/Test
Storm	95,316	59,157	Train/Test
Waledac	81,778	5,765	Train/Test
Zeus	43,593	2,751	Unseen test
Nugache	51,428	49	Unseen test