03-05-2014, 12:57 PM
Sleuthing Junk e-mail automata process in outgoing messages
Sleuthing Junk e-mail automata .pptx (Size: 394.51 KB / Downloads: 14)
Abstract
Compromised machines are one of the key security threats on the Internet
WE focus on the detection of the compromised machines that are involved in the spamming activities known as spam zombies
We develop an effective spam zombie detection system named SPOT
SPOT is designed based on a powerful statistical tool called Sequential Probability Ratio Test
In addition, we also evaluate the performance of the developed SPOT system using a two-month e-mail trace collected in a large US campus network
Proposed System
In this paper we develop a spam zombie detection system SPOT, by monitoring outgoing messages
SPOT is designed based on Probability Ratio Test (SPRT)
SPRT is a powerful statistical method that can be used to test between two hypotheses
SPOT detection system can identify a compromised machine quickly.
Existing System
Xie et al. developed DBSpam to detect proxy-based spamming
BotHunter is developed by GU Et Al., detects compromised machines
An anomaly-based detection system named BotSniffer identifies botnets by exploring the spatial-temporal behavioral similarity commonly observed in botnets
BotMiner is one of the first botnet detection systems that are both protocol and structure independent
Drawback:
These approaches cannot support the online detection requirement in the network environment.
Lack of effective method to detect bots in local networks