Graption: A graph-based P2P traffic classification framework for the internet backbone

2011 ◽  
Vol 55 (8) ◽  
pp. 1909-1920 ◽  
Author(s):  
Marios Iliofotou ◽  
Hyun-chul Kim ◽  
Michalis Faloutsos ◽  
Michael Mitzenmacher ◽  
Prashanth Pappu ◽  
...  
Keyword(s):  
The Internet ◽  
Traffic Classification ◽  
Internet Backbone ◽  
Classification Framework

scholarly journals Graph-Based P2P Traffic Classification at the Internet Backbone

2009 ◽  
Author(s):  
Marios Iliofotou ◽  
Hyun-chul Kim ◽  
Michalis Faloutsos ◽  
Michael Mitzenmacher ◽  
Prashanth Pappu ◽  
...  
Keyword(s):  
The Internet ◽  
Traffic Classification ◽  
Internet Backbone

scholarly journals Robot Communication: Network Traffic Classification Based on Deep Neural Network

2021 ◽  
Vol 15 ◽  
Author(s):  
Mengmeng Ge ◽  
Xiangzhan Yu ◽  
Likun Liu
Keyword(s):  
Neural Network ◽  
Network Traffic ◽  
Short Term Memory ◽  
Traffic Classification ◽  
Classification Framework ◽  
Network Traffic Classification ◽  
Scalar Input ◽  
Memory Network ◽  
Encrypted Traffic ◽  
Robot Communication

With the rapid popularization of robots, the risks brought by robot communication have also attracted the attention of researchers. Because current traffic classification methods based on plaintext cannot classify encrypted traffic, other methods based on statistical analysis require manual extraction of features. This paper proposes (i) a traffic classification framework based on a capsule neural network. This method has a multilayer neural network that can automatically learn the characteristics of the data stream. It uses capsule vectors instead of a single scalar input to effectively classify encrypted network traffic. (ii) For different network structures, a classification network structure combining convolution neural network and long short-term memory network is proposed. This structure has the characteristics of learning network traffic time and space characteristics. Experimental results show that the network model can classify encrypted traffic and does not require manual feature extraction. And on the basis of the previous tool, the recognition accuracy rate has increased by 8%

Cognitive Social Exchange

2019 ◽  
pp. 273-288
Author(s):  
Sampoornam K. P.
Keyword(s):  
Social Exchange ◽  
Error Control ◽  
The Internet ◽  
Receiver Side ◽  
Internet Backbone ◽  
Transmission Switching ◽  
Switching Unit ◽  
Telecommunications Network

This book chapter presents the role of telecommunications network in voice and data transmission. Switching, signaling and transmission are the technologies used to carry out this process. In landline call establishment, calls are routed from subscriber handset to a remote switching unit (RSU), a main switching unit (MSU), and to the internet protocol trunk automated exchange (IPTAX). Then, it is directed to the National Internet Backbone (NIB). On the receiver side, the IPTAX receives this signal from the NIB and directs to it to the MSU and RSU, respectively. The receiver side RSU delivers the information to the destination subscriber. In order to transmit the information from one place to other, it undergoes various process like modulation, demodulation, line coding, equalization, error control, bit synchronization and multiplexing, digitizing an analog message signal, and compression. This chapter also discusses the various services provided by BSNL and agencies governing the internet. Finally, it focuses on the National Internet Backbone facility of BSNL, India.

Network Infrastructure: The Internet Backbone

2004 ◽  
pp. 63-77
Author(s):  
Joan E. Ricart-Costa ◽  
Brian Subirana ◽  
Josep Valor-Sabatier
Keyword(s):  
The Internet ◽  
Network Infrastructure ◽  
Internet Backbone

TRAWLING TRAFFIC UNDER ATTACK OVERCOMING DDoS ATTACKS BY TARGET-CONTROLLED TRAFFIC FILTERING

2011 ◽  
Vol 22 (05) ◽  
pp. 1073-1098
Author(s):  
SHLOMI DOLEV ◽  
YUVAL ELOVICI ◽  
ALEX KESSELMAN ◽  
POLINA ZILBERMAN
Keyword(s):  
Denial Of Service ◽  
The Internet ◽  
Traffic Classification ◽  
Classification Rules ◽  
Ddos Attacks ◽  
Dos Attack ◽  
Dos Attacks ◽  
Worst Case ◽  
Filtering Algorithm ◽  
Internet Community

As more and more services are provided by servers via the Internet, Denial-of-Service (DoS) attacks pose an increasing threat to the Internet community. A DoS attack overloads the target server with a large volume of adverse requests, thereby rendering the server unavailable to "well-behaved" users. In this paper, we propose two algorithms that allow attack targets to dynamically filter their incoming traffic based on a distributed policy. The proposed algorithms defend the target against DoS and distributed DoS (DDoS) attacks and simultaneously ensure that it continues to serve "well-behaved" users. In a nutshell, a target can define a filtering policy which consists of a set of traffic classification rules and the corresponding amounts of traffic for each rule. A filtering algorithm is enforced by the ISP's routers when a target is being overloaded with traffic. The goal is to maximize the amount of filtered traffic forwarded to the target, according to the filtering policy, from the ISP. The first proposed algorithm is a collaborative algorithm which computes and delivers to the target the best possible traffic mix in polynomial time. The second algorithm is a distributed non-collaborative algorithm for which we prove a lower bound on the worst-case performance.

Two different approaches for providing QoS in the Internet backbone

2006 ◽  
Vol 29 (18) ◽  
pp. 3957-3969 ◽  
Author(s):  
P. Giacomazzi ◽  
L. Musumeci ◽  
G. Saddemi ◽  
G. Verticale
Keyword(s):  
The Internet ◽  
Internet Backbone

scholarly journals Robust Face Recognition for Data Mining

2008 ◽  
pp. 3621-3629
Author(s):  
Brian C. Lovell ◽  
Shaokang Chen
Keyword(s):  
Data Mining ◽  
Interactive Television ◽  
Multimedia Data ◽  
The Internet ◽  
Data Types ◽  
Text Documents ◽  
Text Data ◽  
Internet Backbone ◽  
Large Databases ◽  
Robust Face Recognition

While the technology for mining text documents in large databases could be said to be relatively mature, the same cannot be said for mining other important data types such as speech, music, images and video. Yet these forms of multimedia data are becoming increasingly prevalent on the Internet and intranets as bandwidth rapidly increases due to continuing advances in computing hardware and consumer demand. An emerging major problem is the lack of accurate and efficient tools to query these multimedia data directly, so we are usually forced to rely on available metadata, such as manual labeling. Currently the most effective way to label data to allow for searching of multimedia archives is for humans to physically review the material. This is already uneconomic or, in an increasing number of application areas, quite impossible because these data are being collected much faster than any group of humans could meaningfully label them — and the pace is accelerating, forming a veritable explosion of non-text data. Some driver applications are emerging from heightened security demands in the 21st century, post-production of digital interactive television, and the recent deployment of a planetary sensor network overlaid on the Internet backbone.

Sign in / Sign up

Export Citation Format

Share Document