Papers by Keyword: Intrusion Detection

Abstract: Smart homes continuously grow in popularity and effectiveness, however, the interconnection of devices raises concerns over intrusion detection. The amount of smart devices continues to expand and the complexity of the intrusion detection systems needs to equally match these wide intruder capable environments. This article focused on this need by proposing a new solution, which is a hybrid intrusion detection system consisting of autoencoder based feature extraction and Long Short-Term Memory (LSTM) neural network in its classification phase. The entire process included a total data preprocessing stage that had various processes such as the normalization, data shuffling, data partitioning, data cleaning and label splitting and others. These processes were effective in achieving the objectives of the study. The proposed methodology was demonstrated through the application of the famous ‘NSL-KDD’ dataset where training achieved a significant accuracy of 99.467% while the test dataset produced an accuracy of 99.391%. This research is important not only because of its high accuracy but also because of the robust added value it provides to smart home protection. Enabling an autoencoder on a data set allowed us to emphasize specific features and therefore lower the dimensionality space remaining useful information. In addition, the further use of trained LSTM networks allowed the system to understand even more complex sequences of normal and hostile actions done by users improving the prediction. Furthermore, the strictly followed data preprocessing steps made sure that the model was exposed to good and reasonable data, which is an important factor for the efficiency and applicability of any IDS.

Abstract: This research investigates the integration of Global System for Mobile Communications (GSM), laser technology, Arduino microcontrollers, and Light Dependent Resistors (LDR) to develop an active laser sensor security system for homes. The system activates when doors and windows are closed, whether locked or not, by utilizing an active laser detector connected to a microcontroller. This microcontroller interprets the detector's signal state, triggering an alarm through the laser and sending a call signal to a mobile phone via a GSM module if the laser beam is interrupted. By integrating these technologies, the paper offers a promising solution for improving home security and showcases potential innovative applications in electronics and telecommunications. The alert device automatically begins to ring whenever a person or object crosses in front of the laser light. The laser beam is nearly undetectable and may travel great distances without experiencing any scattering. When it detects any irregular activity, a laser security system can function as a stand-alone device that emits noise or commotion. It can also be a component of a larger security system or any other automation system that can notify users.

Abstract: In Nigeria's residential communities, there is an inequity in electricity distribution systems and a lack of transparency in billing practices. Furthermore, traditional solar panels have limited efficiency due to their static positioning, which results in minimal energy capture. This paper proposes a dual-system approach that integrates a smart solar tracking system with a peer-to-peer (P2P) energy-sharing platform to enhance renewable energy capture, ensure fair power distribution, and provide an avenue for income generation. An Arduino Uno microcontroller was used for the solar tracking system, light-dependent resistors (LDRs) were used to measure the intensity of the sun, and servo motors were used to align solar panels for optimal sunlight exposure, thereby improving energy capture efficiency by up to 60%. The P2P energy distribution system, managed by an ESP32 microcontroller, enables equal and monitored energy sharing among tenants through a web dashboard and adaptive energy distribution algorithms. An intrusion detection system, utilizing an ultrasonic sensor, was used to alert the owner in the event of hardware tampering. The system's ability was confirmed through early testing, which supports essential energy needs, such as lighting and device charging, while promoting equitable access to energy. This project demonstrates the potential of combining smart solar tracking with a monitored P2P energy-sharing network to address Nigeria's energy challenges. The plan is to focus on prototype development, field testing, and scaling for broader adoption.

Abstract: A Cyber-attack is a deliberate intent to take illegal access to one’s computer and data. The ascent of the web has turned into the groundwork of the vast majority's day-to-day schedules, and online administration has raised security worries. The rising measure of information, dividing among the cloud and the clients, additionally makes an attack surface. The attack surface has likewise extended with the ascent of organizations and the rising number of individuals utilizing them. The capacity of existing discovery plans to approve the goal and the earlier acknowledgment of assaults is falling apart. In the event that no effective assurance mechanism is carried out, the web will turn out to be substantially more helpless, expanding the gamble of information spillage or hacking. The focus here is to put forward a model (IDS) that detects network intrusions or anomaly detection by classifying all the network traffic packets as non-attack (harmless) or attack (vindictive) classes and also classifying the type of malicious classes using Support Vector Machine algorithm. The machine learning algorithm Support Vector Machine works for classification as well as regression problems. Decision boundaries are usually used in Support Vector Classification (SVC). We have used two different datasets of cybersecurity, namely KDDCUP 1999 and UNSW_NB15. The proposed model has been evaluated using performance metrics, namely accuracy, precision, recall (Detection rate), and F-measure. The test results exhibit that our framework has better identification execution for various cyberattacks. This model achieves an accuracy of 99.8 percent with the KDDCUP 1999 dataset and 98.2 percent with the UNSW_NB15 dataset, and remarkable detection rates of attacks.

Abstract: The issue of intrusion detection has been an active topic in both military and civilian areas, and a great many relevant algorithms and techniques have been developed accordingly. This paper addresses a novel technique based on non-subsampled shearlet transform (NSST) domain artificial neural networks (ANN) to solve the above problem, employing multi-scale geometry analysis (MGA) of NSST and the train characteristics of ANN together. Experimental results indicate that, compared with other existing conventional intrusion detection tools, the proposed one is superior to other current popular ones in both aspects of iteration numbers and convergence rates.

Abstract: In this paper, an efficient anomaly analysis method that is proved to be more efficient and less complex than the existing techniques has been proposed. The approach relies on monitoring the security state by using a set of accurate metrics. The Non-Subsampled Shearlet Transform (NSST) is used to decompose these metrics. Attacks are viewed as singularities that arise in some specific points of time. Therefore, the anomaly detection process is performed through processing the signals representing the metrics. Experimental results indicate that the proposed technique is effective and promising.

Abstract: At present, the issue of intrusion detection has been a hot point to all over the computer security area. In this paper, a novel intrusion detection method has been proposed. Unlike the current existent detection methods, this paper combines the theories of both intuitionistic fuzzy sets (IFS) and artificial neural networks (ANN) together, which leads to much fewer iteration numbers, higher detection rates and sufficient stability. Experimental results show that the now method proposed in this paper is promising and has obvious superiorities over other current typical ones.

Abstract: Intrusion detection system as a proactive network security technology, is necessary and reasonable to add a static defense. However, the traditional exceptions and errors detecting exist issues of leakage police, the false alarm rate or maintenance difficult. In this paper, The intrusion detection system based on data mining with statistics, machine learning techniques in the detection performance, robustness, self-adaptability has a great advantage. The system improves the K-means clustering algorithm, focus on solving two questions of the cluster center node selection and discriminating of clustering properties, the test shows that the system further enhance the detection efficiency of the system.

Abstract: On the basic of multiple populations of immune algorithm and clonal selectionalgorithm, the purpose of this paper is to further improve the detectionefficiency and reducing the false alarm rate. This paper uses the kddcup99 dataset as the experimental data set, and chooses four types of attack data groupof experiment data set as initial population of multiple populations of clonalselection algorithm, through the algorithm to create the optimal model. Basedon the principle of normal data larger than the abnormal data, in turn,experimental data set matched with the normal data set and the optimal model bythe improved R matching algorithm. The results of this paper show that thedetection rate increased significantly

Abstract: With the rapid development of computer networktechnology, and also can be used as well as the increasing number of users ofcomputer network, how to effectively guarantee the network information securitybecomes a key technology of computer network. This paper through the literatureinvestigation method to build the information system security risk evaluationindex system, and combining the expert evaluation process could not get all theinformation in the information system security, a method of information systemsecurity risk assessment is put forward. Was carried out on the key technologyof information system based on big data discussion and analysis, and brieflyintroduces its development prospects. Secondly illustrates the necessity ofintrusion detection, and the concept of intrusion detection and the model isgiven. Finally summarizes many kinds of intrusion detection method and thesystem structure, discusses the existing problems of this field and theresearch direction in the future.