Network Traffic Classification Using Correlation Information

By Jun Zhang, Yang Xiang, Yang Wang, Wanlei Zhou, Yong Guan. IEEE Transactions on Parallel and Distributed Systems, 2013

335 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6ec2e441e8fa363090b3bbfdf5bb4507c3220eeb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qing-Long Han
2. Jun Zhang
3. Yang Xiang
4. Aunn Raza
5. Ala Al-Fuqaha
6. Hunain Arif
7. Amir Hussain
8. Fannia Pacheco

In Computer Networks and Communications

1. Yang Xiang
2. Qing-Long Han
3. Jun Zhang
4. Ala Al-Fuqaha
5. Sheng Wen
6. Surya Nepal
7. Junaid Qadir
8. Wanlei Zhou

In Computer Vision and Pattern Recognition

1. Aunn Raza
2. Ala Al-Fuqaha
3. Hunain Arif
4. Amir Hussain
5. Wei Luo
6. Surya Nepal
7. Junaid Qadir
8. Yehia Elkhatib

Citations in the corpus

• A Survey of Android Malware Detection with Deep Neural Models (2020, background): “However, the feature engineering process is time-expensive and error-prone, and the produced hand-crafted features are task-specific and often subjective to individual judgment [3, 4].”
• Correlated Differential Privacy: Hiding Information in Non-IID Data Set (2015, background): “To preserve -differential privacy, the randomization mechanism M will add independent noise to the count.”
• Software Vulnerability Detection Using Deep Neural Networks: A Survey (2020, background): “[124] J.”
• Towards the Deployment of Machine Learning Solutions in Network Traffic Classification: A Systematic Survey (2019, positive): “Several works already tested the advantages of using BoFs to improve the performance using ML classification and clustering approaches [105]–[107].”
• Detecting and Preventing Cyber Insider Threats: A Survey (2018, background): “Network core equipments such as routers, switches, load balancers and firewalls all have the ability to collect the network traffic passing through which, traditionally, are considered the major audit data sources for detecting intrusions [86]–[91].”
• Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges (2017, methodology): “In 2013, another novel strategy for traffic classification known as network traffic classification using correlation was proposed [167], which uses non-parametric NN combined with statistical measurement of correlation within data to efficiently classify traffic.”