Malware traffic classification using convolutional neural network for representation learning
Citations
975 citations
Cites methods from "Malware traffic classification usin..."
...[200] Malware traffic classification Traffic extracted from 9 types of malware Superivised CNN Oulehla et al....
[...]
...[200] Malware traffic classification CNN SGD First work to use representation learning for malware classification from raw traffic Aceto et al....
[...]
...CNNs have also been used to identify malware traffic, where work in [200] regards traffic data as images and unusual patterns that malware traffic exhibit are classified by representation learning....
[...]
...Network Security [165], [200], [286], [320]–[344], [344]–[350] Signal Processing [273], [308], [310], [351]–[367] Emerging Applications [368]–[372]...
[...]
676 citations
496 citations
Cites methods or result from "Malware traffic classification usin..."
...In summary, the best type of traffic representation is session + all layers, and this conclusion is consistent with our previous findings of [6]....
[...]
...The preprocess tool is USTC-TL2016 developed by our team in [6], consisting of four steps: traffic split, traffic clean, image generation and IDX conversion....
[...]
...Our team proposed a malware traffic classification method with 2D-CNN [6]....
[...]
...Recently, there are some researches about applying CNN in network traffic analysis, such as malware classification by our team [6]....
[...]
...Based on the traffic classification taxonomy proposed by [6], they are both machine learning approaches, whose general workflow is as follows: firstly hand-designing the traffic features (e....
[...]
398 citations
Cites methods or result from "Malware traffic classification usin..."
...Combining the previous research results [13], [48], we conclude that deep neural networks can automatically learn features directly from raw network traffic data and achieve good results in the field of intrusion detection or network anomaly detection....
[...]
...[13] used a CNN to learn the spatial features of network traffic and achievedmalware traffic classification using the image classification method....
[...]
359 citations
References
[...]
46,982 citations
[...]
38,208 citations
11,201 citations
"Malware traffic classification usin..." refers background in this paper
...Representation learning is a new rapidly developing machine learning approach in recent years that automatically learning features from raw data and to a certain extent has solved the problem of hand-designing features [4]....
[...]
10,447 citations
3,300 citations
"Malware traffic classification usin..." refers background in this paper
...The following part introduces how to select traffic granularity and packet layers in our approach....
[...]
...Part I contains ten types of malware traffic from public website which were collected from real network environment by CTU researcher from 2011 to 2015 [16]....
[...]