Fig 3 - uploaded by Carlos Catania
Content may be subject to copyright.
Random Forest performance with incremental training data 

Random Forest performance with incremental training data 

Source publication
Conference Paper
Full-text available
The problem of detecting malicious behavior in network traffic has become an extremely difficult challenge for the security community. Consequently, several intelligence-based tools have been proposed to generate models capable of understanding the information trav-eling through the network and to help in the identification of suspicious connection...

Contexts in source publication

Context 1
... idea behind this experiment is to analyze the impact of incrementing the number of data in training set. Specifically, we evaluate the F1 score metric by each iteration of RF. Figure 3 shows that as the number of data in the training set increases, the mean of F1 score improves. On the X-axis we have the different sizes in training set. ...
Context 2
... start using this extension inside RiskID tool, some connections need to be labeled previously. The Figure 3 has shown that is not necessary much data for train our strategy and get good results. Once the new extension starts to suggest probability of botnet for each connection the users will have a new evaluation criterion. ...
Context 3
... the new extension starts to suggest probability of botnet for each connection the users will have a new evaluation criterion. This favors the increase of connections that will be used to train and as we saw in Figure 3 this improve the detection performance. In this way, the new extension proposed in this article decreases the labeling time of the analyzed dataset. ...

Similar publications

Article
Full-text available
Network security has been included in the 13th five-year plan, and has been put to an unprecedented level of attention. In order to solve the breakdown at the substation end of the power grid, a solution is designed to combine the station end, the data transmission network end and the production control cloud end. First, establish a public cloud fo...
Article
Full-text available
Deep learning based malware classification gains momentum recently. However, deep learning models are vulnerable to adversarial perturbation attacks especially when applied in network security application. Deep neural network (DNN)-based malware classifiers by eating the whole bit sequences are also vulnerable despite their satisfactory performance...
Article
Full-text available
Network traffic classification that is widely applicable and highly accurate is valuable for many network security and management tasks. A flexible and easily configurable classification framework is ideal, as it can be customized for use in a wide variety of networks. In this paper, we propose a highly configurable and flexible machine learning tr...
Preprint
Full-text available
This article presents a primer/overview of applications of Artificial Intelligence and Machine Learning (AI/ML) techniques to address problems in the domain of computer networking. In particular, the techniques have been used to support efficient and accurate traffic prediction, traffic classification, anomaly detection, network management, network...
Thesis
Full-text available
Network security is a crucial topic nowadays as huge amount of data is communicated via computer on a daily basis. Leakage of secret data, software damage or modified information are only some examples of potential threats which cost millions of dollars every year. Development of quality intrusion detection systems can save a lot of unnecessary exp...