Detecting and Classifying Attacks using Artificial Neural Network

The ubiquity of the Internet poses serious concerns on the security of computer infrastructures and the integrity of sensitive data. Intrusion Detection Systems (IDS) aim at protecting networks and computers from malicious networkbased or host-based attacks. The underlying assumption of intrusion detection is an attack will noticeably affect system performance or behavior. Neural networks method is a promising technique, which has been used in many classification problems. The present study is aimed to solve a multi-class problem of intrusion detection using MLP in which not only the attack records are distinguished from normal ones, but also the attack type is identified. The results showed that the designed system is capable of classifying records with 93.43% accuracy with two hidden layers of neuron.

A decent method to identify ill-conceived use is through checking unordinary client action. Techniques for interruption identification dependent close by coded rule sets or foreseeing directions on-line are laborous to construct or not truly solid. This paper proposes another method for applying neural systems to identify interruptions. In the proposed technique, rather than thinking about all highlights for interruption recognition and burning through up the time in investigating it, just the important component for the specific assault is chosen and interruption discovery is finished with assistance of managed learning Neural Network (NN). The element determination is finished with the assistance of data gain calculation and hereditary calculation .The Multi Layer Perceptron (MLP) managed NN is utilized to prepare the significant highlights alone in our proposed framework. This framework improves the Detection Rate (DTR) for a wide range of assaults when contrasted with Intrusion identification framework which utilizes all highlights and chose highlights utilizing hereditary calculation with MLP NN as the classifier. Our proposed framework results, in distinguishing interruptions with higher exactness, particularly for Remote to Local (R2L), User to Root (U2R) and Denial of Service (DoS) assaults.

2017

Nowadays the computer security is important in our society,. Because of the wide use of computer networks and its application, it becomes imperative to detect the network attacks to protect the information security.therefor, anyone using a computer is at some risk of intrusion, even if he is not connected to the Internet or any other network . If the computer is left unattended, any person can attempt to access and misuse the system. The problem is, however, greater if the computer is connected to a network, especially the Internet. Any user from any place in the world can reach the computer remotely and may attempt to access private information. Solving the problem of attack detection using intrusion detection against computer networks is being a major problem in the area of network security. The intrusion detection system meets some challenges, and there are different approaches to deal with these challenges, neural network and machine learning is the best approaches to deal with ...

SSRN Electronic Journal, 2019

With the advancement in technology and over internet, the number of attacks through unauthorized access has also increased. For fighting these attacks and to ensure the safety of the system, powerful Intrusion Detection System (IDS) is required. IDS's are used for sensing the attack persisting inside the network system. This paper reviews different existing Intrusion Detection Systems using Artificial Neural Networks for detecting malicious network activity as the success of neural networks comes from the fact that they are able to learn a number of behaviours depending on network input. They are very effective and fast in classification and can easily identify new threats. One of the features that uphold neural networks in the field of intrusion detection is its flexibility to adapt to any environment. This work evaluates the parameters that play the major role in enhancing the efficiency and accuracy of IDS.

2013

Information is an important asset of an organization. Large amount of information need to be stored and processed in network based computers. The confidentiality, integrity and availability of the system resources have raised the vulnerability of these systems to security threats, attacks and intrusions. One idea is to use a neural network algorithm for detecting intrusions. The neural network algorithms are popular for their ability to ’learn’ the patterns in a given environment and thus can be trained to detect intrusions by recognizing patterns of an intrusion. In this work we perform a comparative study of Multilayer Feed Forward, Elman Back Propagation, Cascaded Forward Back Propagation and Self Organizing Feature Map neural networks based intrusion detection systems. In this study we work on the well structured KDD CUP 99 dataset.

PROF MUHAMMAD NAFIU , 2024

Network security is becoming an issue of paramount importance in the information technology era. Nowadays with the dramatic growth of communication and computer networks, security has become a critical subject for computer system. Intrusion detection is the art of detecting computer abuse and any attempt to break the networks. Intrusion detection system is an effective security tool that helps to prevent unauthorized access to applications are created and implemented to solve the problem of detecting the attacks in intrusion detection systems. Most methods detect attacks and categorize in two groups, normal or threat. One of the most promising areas of research in the area of Intrusion Detection deals with the applications of the Artificial Intelligence (AI) techniques. This proposed system presents a new approach of intrusion detection system based on artificial neural network. Architecture is used for Intrusion Detection System. The performance and evaluations are performed by using the set of benchmark data from a KDD (Knowledge discovery in Database) dataset. The proposed system detects the attacks and classifies them in six groups.

2019

Information systems are one of the areas where public and private sector invested the most in recent years. Almost every area of life, including critical infrastructure systems (electricity, water, telecommunications, banking, etc.), is managed by information systems. These developments provide an environment for the rapid increase of cyber-attacks and their application in very different ways. In this study, Intrusion Detection Systems, one of the basic elements for information security, will be evaluated and the results obtained from a sample ANN based IDS application will be analyzed.

Intrusion Detection is the task of detecting, preventing and possibly reacting to the attack and intrusions in a network based computer systems. In the literature several machine-learning paradigms have been proposed for developing an Intrusion Detection System. This paper proposes an Artificial Neural Network approach for Intrusion Detection. A Feed Forward Neural Network trained by Back Propagation algorithm is developed to classify the intrusions using a profile data set (ten percent of the KDD Cup 99 Data) with the information related to the computer network during Normal behavior and during Intrusive (Abnormal) behavior. Test result shows that the proposed approach works well in detecting different attacks accurately with less false positive and negative rate and it is comparable to those reported in the literature.

2014

Intrusion detection is a process that analyzes abnormalities in system or network activities. For security purpose it is necessary to identify malicious events correctly. Majority of research is going on neural network and machine learning technique for detecting intrusions. Several researchers used back propagation neural network approach for their experimentation. Mostly they have used KDDCup'99 dataset and classified the events into major attack classes i.e. DoS, U2R, R2L and Probe. But for security experts it is necessary to identify the attack type to quickly take particular action on it. Therefore the current research work is to detect and classify instance into its specific attack type. In this research paper, using KDDCup'99 dataset, instances are classified into 23 attack types. Back propagation neural network (BPN) classifier is built for classification with the help of "Waikato Environment for Knowledge Analysis (WEKA)" library and evaluated by observing detection rate. Results showed that it classifies instances into several attack types with low detection rate.

International Conference on Aerospace Sciences and Aviation Technology, 2003

Intrusion detection systems (IDS) have become an essential issue for computer networks security since each one is vulnerable for violation. This paper presents a neural network based implementation of an intrusion detection system to detect network based attacks. The key idea is to extract the most useful set of features from the packets traversing through the network and utilize them to describe users behavior. These selected features will be used an input features to train a designed neural network architecture to build a classifier that can recognize anomalies and known intrusions. Using a benchmark data set from a KDD (Knowledge Discovery and Data Mining), the designed system was able to correctly detect 99.8% of unusual network activity with a maximum of 5.4% false alarms. In addition, the system was 98.6% accurate in detecting different intrusion types.

ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal

In this paper, some of the methods used in the intrusion detection system were described using the neural network as a tool in intrusion detection system, which became very necessary in computer systems because it provides protection against attacks by hackers that are becoming increasingly destructive to computer systems.The Backpropagation Neural Network was chosen from among the neural networks due to its ability, speed and intelligence to recognize packet patterns captured from the network, providing the ability to detect intrusion of the system. The speed of the network in giving the diagnosis is one of the most important reasons for choosing the neural network. Therefore, many Attacks features have been analyzed of the standard packets that allow traffic through the network as well as the unusual packets, especially on these protocols (TCP, UDP).The results of these analyzes have been used to learn the neural network on the structure and pattern of standard and unusual packets...

2009

Intrusion detection is the art of detecting computer abuse and any attempt to break into networks. As a field of research, it must continuously change and evolve to keep up with new types of attacks or adversaries and the ever-changing environment of the Internet. To render networks more secure, intrusion-detection systems aim to recognize attacks within the constraints of two major performance considerations: high detection and low false-alarm rates. It is also not enough to detect already-known intrusions, yet-unseen attacks or variations of those known present a real challenge in the design of these systems. Intrusion-detection systems are firmly entrenched on the security front but the exact role they can play and what their deployment entails must be clear to planners of security. They implement a solution to a multifaceted problem and to be efficient in a given environment may require a combination of detection methods.

The International Journal of FORENSIC COMPUTER SCIENCE IJOFCS, 2008

In this paper, we present concepts in artificial neural networks (ANN) to help detect intrusion attacks against network computers, and introduce and compare a multi-layer perceptron ANN (MLPANN) with Snort, an open-source tool for intrusion detection systems (IDS). To conduct these comparison experiments, we inserted malicious traffic into the MLPANN to train our ANN, with results indicating that our ANN detected 99% of these input attacks.