On the performance of DPI signature matching with dynamic priority

Melo, Wesley; Lopes, Petronio; Antonello, Rafael; Fernandes, Stênio; Sadok, Djamel

doi:10.1109/iscc.2014.6912553

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The traditional traffic identification methods include the deep packet inspection [2][3][4][5] and the deep flow inspection. The traditional traffic identification methods include the deep packet inspection [2][3][4][5] and the deep flow inspection.…”

Section: Introductionmentioning

confidence: 99%

“…At present, dynamic internet protocol, dynamic ports, and fake ports are often used in the process of network communication. The traditional traffic identification methods include the deep packet inspection [2][3][4][5] and the deep flow inspection. [6][7][8] For the encryption traffic identification, the traditional identification method was faced with a series of issues.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online and automatic identification of encryption network behaviors in big data environment

Zhu

2018

Concurrency and Computation

View full text Add to dashboard Cite

To handle the difficulty in identifying encrypted network traffic in big data environment, a fast and online identification method for encryption network behaviors was proposed. Twitter audios, messages, videos, images, and other encrypted network behaviors were deeply studied in big data environment, and the features were extracted from a lot of encryption network behaviors, and the model database based on the correlation coefficient was established by these features, and the correlation coefficient between the network interactive data and the model database was calculated by acquiring the network interactive data at real time. The reference distance will be proposed and used to eliminate the noise of similar traffic sets; at last, the automatic and online identification of encryption network behaviors based on correlation coefficient and reference distance in big data environment were implemented by combination with the classification threshold, and the online identification rate was about 93% by this method, and the experiment results show the proposed method is applicable and effective.

show abstract