Early application identification

By Laurent Bernaille, Renata Cruz Teixeira, Kave Salamatian. Conference on Emerging Network Experiment and Technology, 2006

444 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/c3949577fee310a22f76f3b4a0004ee7be079017

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. Michalis Faloutsos
2. Antonio Pescapè
3. K. Claffy
4. Mohammad Ali Salahuddin
5. Maurizio Dusi
6. Antonello Rizzi
7. Sara Ayoubi
8. Anirban Mahanti

In Computer Networks and Communications

1. Antonio Pescapè
2. Giuseppe Aceto
3. Michalis Faloutsos
4. K. Claffy
5. Mohammad Ali Salahuddin
6. Maurizio Dusi
7. Antonello Rizzi
8. Sara Ayoubi

In Hardware and Architecture

1. K. Claffy
2. Maurizio Dusi
3. Anirban Mahanti
4. Raouf Boutaba
5. Francesco Gringoli
6. Luca Salgarelli
7. Alberto Dainotti
8. Hyunchul Kim

Citations in the corpus

• A Survey on Internet Traffic Identification (2009, methodology): “Bernaille et al [ 60 ][61][62] perform traffic classification based on packet headers.”
• Internet traffic classification demystified: myths, caveats, and the best practices (2008, methodology): “Previous efforts on flowfeatures-based classification [29, 31, 36, 9, 16, 7, 14, 42, 20, 39] have shown that bidirectional TCP flow statistics provide such fingerprints for various applications.”
• Offline/realtime traffic classification using semi-supervised learning (2007, background): “Prior studies focused on traces with limited number of applications: 10 in [2] and only 3 in [7].”
• Real Time Identification of SSH Encrypted Application Flows by Using Cluster Analysis Techniques (2009, methodology): “[7] use faster clustering algorithms representing data in different spaces: K-means and Gaussian Mixture Models (GMM) for euclidean space and Spectral clustering in HMM based space.”
• A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, methodology): “However, this issue can be resolved by leveraging port number as a feature during cluster composition [56], which increases the classification accuracy of POP3 to over 90%.”
• Traffic classification through simple statistical fingerprinting (2007, methodology): “[14] proposes the use of three clustering techniques to achieve fine-grained classification based on size and direction of packets.”
• Support Vector Machines for TCP traffic classification (2009, methodology): “A fine-grained classification based on clustering techniques is proposed by Bernaille et al. in [5].”
• Issues and future directions in traffic classification (2012, background): “Traffic classification techniques in the literature have not kept pace with these three challenging trends.”
• Mobile Encrypted Traffic Classification Using Deep Learning: Experimental Evaluation, Lessons Learned, and Challenges (2019, background): “Based on the aforementioned categorization, it is worth noticing that all the types of input data considered for DL are naturally suited for “early” TC [43].”
• SubFlow: Towards practical flow-level traffic classification (2012, background): “However, despite significant research efforts [14], [1], [12], these methods have not made the anticipated impact in the real world.”