Data Mining Practical Machine Learning Tools and Techniques

A survey on security attacks in VANETs: Communication, applications and challenges

2014 2nd International Conference on Information and Communication Technology (ICoICT)

In the digitalized modern world in parallel to the new technological developments, information security has become the highest priority in the individual and institutional sense. In order to ensure the security of information systems, various systems are used techniques and technologies, including encryption, authorization, firewall, honeypot based systems. In this study, a honeypot based approach for intrusion detection/prevention systems (ID/PS) is proposed. The developed honeypot server application is combined with IDSs to analyze data in real-time and to operate effectively. Moreover, by associating the advantages of low and high-interaction honeypots, a superior hybrid honeypot system is performed. Therefore, in order to reduce the cost of configuration, maintenance, and management, after viewing the usage of honeypots on corporate networks, virtualization technologies are used. The developed system is a honeypot based intrusion detection and prevention system (IDPS) type and it is able to show the network traffic on servers visually in real-time animation. Thereby, it provides system information easily. Finally, the developed system can detect zero-day attack due to the configuration of intrusion detection, which makes it superior in performance compared to other IDSs. This system also helps in reducing the false positive level in IDSs.

A novel honeypot based security approach for real-time intrusion detection and prevention systems

Hybrid intrusion detection system using machine learning

Attackers are most likely to exploit invalidated and unsanitized user input with several attacks such as cross-site scripting (XSS) or SQL injection. Many methods were proposed to prevent those attacks. Some of them were created to learn about pattern and behavior of the attacker. That is honeypot. Honeypot is classified into two types based on the simulation that honeypot can do: low interaction and high interaction.

Aggressive web application honeypot for exposing attacker's identity

A Study on Intrusion Detection Using Centroid-Based Classification

Epilepsy is a neurological disorder of the brain that can generate epileptic seizures when abnormal excessive activity occurs in the brain. The seizure is marked by brief episodes of involuntary movement of the body, and sometimes followed by unconsciousness. In this study, the EEG classification system was performed to predict whether EEG signals belong to normal individuals, epileptic patients in seizure free or seizure condition. The EEG dataset contains 5 sets of 100 EEG segments which is referred to as set A to set E. The classification system consisted of three scenarios. One of the scenarios involved the methods of Single Channel Independent Component Analysis (SCICA), power spectrum, and a neural network. The results were compared to the results without implementing SCICA. The last experiment showed the effect of using Linear Discriminant Analysis (LDA) to reduce the features of power spectrum. The results gave the accuracies for 3, 4, and 5 classes. By applying SCICA, all the accuracies were improved significantly with the maximum accuracy of 94 % for 3 classes.

Classification of EEG Signals Using Single Channel Independent Component Analysis, Power Spectrum, and Linear Discriminant Analysis

The measurement of brain electrical activity recorded as EEG signals finds most application in epilepsy. EEG waveforms carry information about the underlying neural system dynamics and show different features amongst epilepsy syndromes. In this research, empirical mode decomposition (EMD) and power spectrum were employed to extract the features from EEG dataset of healthy participants, and epilepsy patients with seizure and seizure free conditions. The recorded EEG signals are represented by 500 signal segments from 5 sets of different conditions. The sum of Intrinsic Mode Function (IMF) power spectrum components gave 10 features for 50 components, and 20 features for 25 components, which were used as the classification inputs for artificial neural networks and random forest classifiers. The classifications were carried out for 3, 4, and 5 classes. From the experiments, the highest average accuracy was obtained for 3 classes using 20 features of power spectrum from the sum of 6 IMFs. For use of 6 IMFs, the accuracies had the maximum values of 92.4%, 90.4%, and 78.6% for 3, 4, and 5 classes respectively. It also improved the accuracy significantly for 5 classes.

Feature extraction using combination of intrinsic mode functions and power spectrum for EEG signal classification

One of the main purposes of data hiding is to secure the messages while transmitting via a public network such as the internet. As known, there are so many types of data hiding such as hiding text inside text, text inside video, and text inside digital image. It is also known that, Difference Expansion has become a powerful method in data hiding using digital images. For instance, it is known that data hiding is needed in so many fields such as health, military, and finance. Especially for reversible data hiding which has the ability to return the same secret data and cover image after the extraction operation. In this paper, we focus on how to increase the capacity of the secret message as high as possible while maintaining the quality of the stego image. We will present a scheme that has modified the previous method by enlarging the pixel blocks to be as a matrix 4 by 4 that can hide 15 bits per block. In addition, we have modified the scheme of RDE to make the difference values smaller since that will bring also a chance for increasing the capacity and may improve the quality of the stego image. The experimental results have shown that the capacity has surely and hugely increased.

Supeno Djanali

Papers

Aggressive web application honeypot for exposing attacker's identity

A Study on Intrusion Detection Using Centroid-Based Classification

Classification of EEG Signals Using Single Channel Independent Component Analysis, Power Spectrum, and Linear Discriminant Analysis

Feature extraction using combination of intrinsic mode functions and power spectrum for EEG signal classification

Increasing the capacity of the secret data using DEpixels blocks and adjusted RDE-based on grayscale images