Discovery of Invariant Bot Behavior through Visual Network Monitoring System

Shahrestani, Alireza; Feily, Maryam; Ahmad, Rodina; Ramadass, Sureswaran

doi:10.1109/securware.2010.37

Cited by 7 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other threats that botnets can create include data theft, tampering with social polls, and the use of bot-infected computer resources [29]. For example, recently, bot resources have been used to process and extract bitcoins, send spam, steal confidential information, as well as infect other computers and spread on the network [8]. The spread of botnet networks and the presence of a large number of infected computers is the main reason why networks are dangerous.…”

Section: Botnetmentioning

confidence: 99%

Botnet detection based on Markov chain and Fuzzy rough set

Ezzatneshan,

Farizani,

Kheirabadi

et al. 2023

Preprint

View full text Add to dashboard Cite

Botnets now make up a wide range of cyber-attacks, which are a network of infected computers connected to the Internet, with remote control. So far, a lot of research has been done in this field, the proposed methods are based on the signatures of discovered botnets, anomalies, traffic behavior, and addresses. Each method has both advantages and disadvantages. This research proposes a structure for performing identification operations, which is presented in this research based on the Markov chain and is based on behavioral analysis. A disadvantage of the past methods is the inability to receive network information at a very high speed. In this research, it has tried using a solution to receive traffic at a very high speed of about 40 Gbps and analyze it. To be able to perform the analysis with a lower overhead. The proposed method can investigate the behavior of botnets by examining the area of behavior better than the previous solutions, and as a result, during the solutions used by botnets to hide their behavior, it can counter and identify suspicious flows. The accuracy of the proposed method was found to be 96.170%.

show abstract

Section: Botnetmentioning

confidence: 99%