Effectiveness of statistical features for early stage internet traffic identification

L Peng, B Yang, Y Chen, Z Chen - International Journal of Parallel …, 2016 - Springer
Identifying network traffic at their early stages accurately is very important for the application
of traffic identification. In recent years, more and more studies have tried to build effective …

Encrypted traffic classification: Combining over-and under-sampling through a pca-svm

A Saber, B Fergani, M Abbas - 2018 3rd International …, 2018 - ieeexplore.ieee.org
VPN (Virtual Private Network) is often the most efficient and the least expensive way to
maintain flexibility, integrity and confidentiality of data exchange over the Internet. It also …

Early online classification of encrypted traffic streams using multi-fractal features

E Areström, N Carlsson - IEEE INFOCOM 2019-IEEE …, 2019 - ieeexplore.ieee.org
Timely and accurate flow classification is important for identifying flows with different service
requirements, optimized network management, and for helping network operators …

Traffic classification using probabilistic neural networks

R Sun, B Yang, L Peng, Z Chen… - … Conference on Natural …, 2010 - ieeexplore.ieee.org
Traffic classification, a branch of passive network measurement, becomes more and more
important for network management. As traditional traffic classification techniques like port …

On-chip Fourier-transform spectrometers and machine learning: a new route to smart photonic sensors

A Herrero-Bermello, J Li, M Khazaei, Y Grinberg… - Optics Letters, 2019 - opg.optica.org
Miniaturized silicon photonics spectrometers capable of detecting specific absorption
features have great potential for mass market applications in medicine, environmental …

Electrostatically doped silicon nanowire arrays for multispectral photodetectors

HD Um, A Solanki, A Jayaraman, RG Gordon… - ACS …, 2019 - ACS Publications
Nanowires have promising applications as photodetectors with superior ability to tune
absorption with morphology. Despite their high optical absorption, the quantum efficiencies …

User participation in social media: Digg study

K Lerman - 2007 IEEE/WIC/ACM International Conferences on …, 2007 - ieeexplore.ieee.org
The social news aggregator Digg allows users to submit and moderate stories by voting on
(digging) them. As is true of most social sites, user participation on Digg is non-uniformly …

A frontier: Dependable, reliable and secure machine learning for network/system management

DC Le, N Zincir-Heywood - Journal of Network and Systems Management, 2020 - Springer
Modern networks and systems pose many challenges to traditional management
approaches. Not only the number of devices and the volume of network traffic are increasing …

[PDF][PDF] Evaluating machine learning algorithms for automated network application identification

N Williams, S Zander… - Center for …, 2006 - researchportal.murdoch.edu.au
The identification of network applications that create traffic flows is vital to the areas of
network management and surveillance. Current popular methods such as port number and …

Browser fingerprinting from coarse traffic summaries: Techniques and implications

TF Yen, X Huang, F Monrose, MK Reiter - … DIMVA 2009, Como, Italy, July 9 …, 2009 - Springer
We demonstrate that the browser implementation used at a host can be passively identified
with significant precision and recall, using only coarse summaries of web traffic to and from …