Research Article
[Retracted] CLD-Net: A Network Combining CNN and LSTM for Internet Encrypted Traffic Classification
| | Input: raw network traffic dataset ; number of traffic classes ; | | | Output: packet matrix ; | | (1) | for each do | | (2) | Randomly select consecutive 10 packets in ; | | (3) | 10 consecutive packets consist a flow , that is, the number of is ; | | (4) | Randomly divide the into a training set and a testing set in proportion; Traffic split; | | (5) | for each do | | (6) | for each packet do | | (7) | Trim and uniform length of 256 bytes, payload ; Traffic clean; | | (8) | Recombine ; Traffic recombination; | | (9) | Generate the grayscale image format to get the packet matrix, ; Traffic conversion; | | (10) | end for; | | (11) | end for; | | (12) | end for; | | (13) | return Packet matrix; |
|