Arvind R. Bhagat Patil

Bio: Arvind R. Bhagat Patil is an academic researcher. The author has contributed to research in topics: Rule-based system. The author has an hindex of 2, co-authored 2 publications receiving 15 citations.

Network Attacks and Their Detection Mechanisms: A Review

Abstract: With the development of large open networks, security threats for the network have increased significantly in the past few years. Different types of attacks possess different types of threats to network and network resources. Many different detection mechanisms have been proposed by various researchers. This paper reviews different type of possible network attacks and detection mechanisms proposed by various researchers that are capable of detecting such attacks. General Terms Network resources, open network, security threats for network

Survey on Classification, Detection and Prevention of Network Attacks using Rule based Approach

Abstract: Intrusion detection systems(IDS) has assumes an important part to protect the qualities of PC mostly into two classifications: malignant and irrelevant exercises. Intrusion detection can be accomplish by Categorization. Another machine learning based algorithm for order of information is actualized to network intrusion detection is presented in this paper. The most basic employment is to separate exercises of network are as ordinary or irrelevant while decreasing the misclassification. The goal of Intrusion detection framework (IDS) are to apply all the accessible data keeping in mind the end goal to distinguish the attacks by outcast programmers and abuse of insiders. For Network intrusion detection there are diverse arrangement models have been produced, the most regularly connected strategies are Support Vector Machine(SVM) and Ant Colony both consider their qualities and shortcomings independently. To diminishes the shortcoming, blend of the SVM technique with Ant Colony to take the advantages ofboth . A standard benchmark of information set KDD99 is assessed and actualized as another algorithm. Despite the fact that to increment both the grouping rate and runtime adequacy it is important to actualize the Combining Support Vectors with Ant Colony which beat SVM alone . An individual continuous network dataset and a notable dataset i.e. KDD99 CUP has been actualized as proposed framework. All attack sorts, detection rate, detection speed, false alert rate can be measured by execution of intrusion detection framework IDS.

A Two-Level Hybrid Model for Anomalous Activity Detection in IoT Networks

Abstract: In this paper we propose a two-level hybrid anomalous activity detection model for intrusion detection in IoT networks. The level-1 model uses flow-based anomaly detection, which is capable of classifying the network traffic as normal or anomalous. The flow-based features are extracted from the CICIDS2017 and UNSW-15 datasets. If an anomaly activity is detected then the flow is forwarded to the level-2 model to find the category of the anomaly by deeply examining the contents of the packet. The level-2 model uses Recursive Feature Elimination (RFE) to select significant features and Synthetic Minority Over-Sampling Technique (SMOTE) for oversampling and Edited Nearest Neighbors (ENN) for cleaning the CICIDS2017 and UNSW-15 datasets. Our proposed model precision, recall and F score for level-1 were measured 100% for the CICIDS2017 dataset and 99% for the UNSW-15 dataset, while the level-2 model precision, recall, and F score were measured at 100 % for the CICIDS2017 dataset and 97 % for the UNSW-15 dataset. The predictor we introduce in this paper provides a solid framework for the development of malicious activity detection in IoT networks.

Network intrusion detection based on deep learning model optimized with rule-based hybrid feature selection

Abstract: Network Intrusion Detection System (NIDS) is often used to classify network traffic in an attempt to protect computer systems from various network attacks. A major component for building an efficie...

Review of Detection DDOS Attack Detection Using Naive Bayes Classifier for Network Forensics

Abstract: Di s tributed Denial of Service (DDoS) is a type of attack using the volume, intensity, and m ore costs m itigation to increase in this era . A ttack ers used many zombie computers to exhaust the resources available to a network, application or service so that authorize users cannot gain access or the network service is down, and it is a great loss for Internet users in computer networks affected by DDoS attacks. In the Network Forensic, a crime that occurs in the system network services can be sued in the court and the attackers will be punished in accordance with law. This research has the goal to develop a new approach to detect DDoS attacks based on network traffic activity were statistically analyzed using Naive Bayes method. Data were taken from the training and testing of network traffic in a core router in Master of Information Technology Research Laboratory University of Ahmad Dahlan Yogyakarta. The new approach in detecting DDoS attacks is expected to be a relation with Intrusion Detection System (IDS) to predict the existence of DDoS attacks.

Using machine learning methods for detecting network anomalies within SNMP-MIB dataset

Abstract: One of the most prevalent network attacks that threaten networks is Denial of Service (DoS) flooding attacks. Hence, there is a need for effective approaches that can efficiently detect any intrusion in a network. This paper presents an efficient mechanism for network attacks detection within MIB data, which is associated with the protocol (SNMP). This paper investigates the impact of SNMP-MIB data in network anomalies detection. Classification approach is used to build the detection model. This approach presents a comprehensive study on the effectiveness of SNMP-MIB data in detecting different types of attack. The Random Forest classifier achieved the highest accuracy rate with the IP group (100%) and with the Interface group (99.93%). The results show that among five MIB groups the Interface and IP groups are the only groups that are affected the most by all types of attack, while the ICMP, TCP and UDP groups are less affected.

Exploiting SNMP-MIB Data to Detect Network Anomalies Using Machine Learning Techniques

Abstract: The exponential increase in the number of malicious threats on computer networks and Internet services due to a large number of attacks makes the network security at continuous risk. One of the most prevalent network attacks that threaten networks is Denial of Service (DoS) flooding attack. DoS attacks have recently become the most attractive type of attacks to attackers and these have posed devastating threats to network services. So, there is a need for effective approaches, which can efficiently detect any intrusion in the network. This paper presents an efficient mechanism for network attacks detection and types of attack classification using the Management Information Base (MIB) database associated with the Simple Network Management Protocol (SNMP) through machine learning techniques. This paper also investigates the impact of SNMP-MIB data on network anomalies detection. Three classifiers, namely, Random Forest, AdaboostM1 and MLP are used to build the detection model. The use of different classifiers presents a comprehensive study on the effectiveness of SNMP-MIB data in detecting different types of attack. Empirical results show that the machine learning techniques were quite successful in detecting and classifying the attacks with a high detection rate.