A HTTP-based dynamic adaptive encryption video traffic identification method
A dynamic self-adaptation and traffic recognition technology, applied in image communication, selective content distribution, electrical components, etc., can solve the problems of being easily affected by noise and high false positives
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0039] As a most basic implementation of the present invention, this embodiment discloses a dynamic adaptive encryption video traffic identification method based on HTTP, including a data acquisition step, a data preprocessing step, a similarity calculation step and a classification and identification step:
[0040] The data acquisition step is to obtain the encrypted video data flow from the network, remove the irrelevant flow in the encrypted video data flow of the known video title, and save it as a training method for data packet burst flow feature extraction and video classification construction data set.
[0041] The encrypted video data flow includes a known title and an original video data flow to be identified, wherein the video data flow of a known title is used to construct a reference benchmark BPP time series, and BPP refers to the time sequence from the server to the client during a complete peak duration. The number of bidirectional transmission bits at the end....
Embodiment 2
[0057] As a preferred implementation of this embodiment, on the basis of Embodiment 1, further, the encrypted video data flow of the known video title and the encrypted video flow to be identified include several videos, and each video contains Both contain several video streams.
[0058] The BPP time series is a time series corresponding to video streams in each video.
[0059] In the data preprocessing step, each peak stage in the encrypted video traffic to be identified is obtained through network monitoring software.
[0060] In the similarity calculation step, the DTW algorithm recursively calculates the DTW value of the jth single video stream in the encrypted video traffic data video i to be identified by the formula of Cost=d(s[i], t[j]) , ie DTW[i, j]=Cost+Minimum(DTW[i-1, j], DTW[i, j-1], DTW[i-1, j-1]), DTW[i, j] The larger the value, the lower the similarity between the corresponding BPP time series and the time series of the data set. If the value of DTW[i, j]=0...
Embodiment 3
[0066] As another preferred implementation of this embodiment, this embodiment discloses an HTTP-based dynamic adaptive encrypted video traffic classification and identification method, including the following steps:
[0067] Step S1, network encrypted video traffic data collection and preprocessing;
[0068] Step S1 comprises the following steps:
[0069] Step S11. Obtain encrypted video data traffic of known video titles from the network, remove irrelevant traffic, and save files for feature extraction of data packet burst traffic to construct a training data set.
[0070] Step S12, preprocessing the data packets, the goal is to form a BPP time series with video title marks, that is, to form a marked BPP sequence for known titles, and to form a BPP sequence for the video traffic to be identified for testing, and the BPP is The number of bits of data packets sent and received by each peak is obtained through the preprocessing of the PCAP file.
[0071] Step S2, calculating ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


