Intrusion Detection Rate Research Articles

A New Multi-Level Semi-Supervised Learning Approach for Network Intrusion Detection System Based on the ‘GOA’

One of the important technologies in present days is Intrusion detection technology. By using the machine learning techniques, researchers were developed different intrusion systems. But, the designed models toughness is affected by the two parameters, in that first one is, high network traffic imbalance in several categories, and another is, non-identical distribution is present in between the test set and training set in feature space. An artificial neural network (ANN) multi-level intrusion detection model with semi-supervised hierarchical [Formula: see text]-means method (HSK-means) is presented in this paper. Error rate of intrusion detection is reduced by the ANN’s accurate learning so it uses the Grasshopper Optimization Algorithm (GOA) which is analysed in this paper. Based on selection of important and useful parameters as bias and weight, error rate of intrusion detection system is reduced in the GOA algorithm and this is the main objective of the proposed system. Cluster based method is used in the pattern discovery module in order to find the unknown patterns. Here the test sample is treated as unlabelled unknown pattern or the known pattern. Proposed approach performance is evaluated by using the dataset as KDDCUP99. It is evident from the experimental findings that the projected model of GOA based semi supervised learning approach is better in terms of sensitivity, specificity and overall accuracy than the intrusion systems which are existed previously.

A Malicious Intrusion Detection Model of Network Communication in Cloud Data Center

To enhance the efficiency of malicious intrusion detection of network communication, a malicious intrusion detection model for the network communication in cloud data center is designed. Firstly, the data preprocessing includes three parts: normal sample data modeling, standard data membership calculation and standard data membership calculation. Then, the characteristic value collection stage is completed. Finally, the intrusion detection classification and trust value calculation are completed to conclude the malicious intrusion detection of the network communication in cloud data center. Exploratory findings show that the malicious intrusion detection model for the network communication in cloud data center improves the intrusion detection rate, and reduces the detection time and false alarm rate.

Cyber-Attack Detection and Mitigation Using SVM for 5G Network

5G technology is widely seen as a game-changer for the IT and telecommunications sectors. Benefits expected from 5G include lower latency, higher capacity, and greater levels of bandwidth. 5G also has the potential to provide additional bandwidth in terms of AI support, further increasing the benefits to the IT and telecom sectors. There are many security threats and organizational vulnerabilities that can be exploited by fraudsters to take over or damage corporate data. This research addresses cybersecurity issues and vulnerabilities in 4G(LTE) and 5G technology. The findings in this research were obtained by using primary and secondary data. Secondary data was collected by reviewing literature and conducting surveys. Primary data were obtained by conducting an experimental simulation using the support vector machine (SVM) approach. The results show that cybersecurity issues related to 4G and 5G need to be addressed to ensure integrity, confidentiality, and availability. All enterprises are constantly exposed to a variety of risks. Also implemented an efficient SVM-based attack detection and mitigation system for 5G network. The proposed intrusion detection system defends against security attacks in the 5G environment. The results show that the throughput and intrusion detection rate is higher while the latency, energy consumption, and packet loss ratio are low, indicating that the proposed intrusion detection and defense system has achieved better QoS. The security solutions are fast and effective in detecting and mitigating cyber-attacks.

Cyber-security threats and vulnerabilities in 4G/5G network enabled systems

In the era of 4G and 5G networks, many cyber-security issues have arisen. Security is an important issue that should not be overlooked. The security system consists of standardisation, network policies, network arrangements and network positioning. This study investigates the challenges related to cyber-security threats and vulnerabilities within 4G/5G networks and how they affect their use. The primary and secondary data analysis indicates that significant regulatory intervention is required to prevent serious cyber-security issues within these networks, in addition, to affecting users' privacy. Compared to the current intrusion detection system, the new intrusion detection system has better QoS. Intrusion detection rates can vary based on the number of nodes arriving in the network. Support vector machines are used to detect and prevent intrusions within a network and to identify attackers inside. In terms of cyber-attack detection and mitigation, the solutions are fast and effective.

A New Intrusion Detection Algorithm AE-3WD for Industrial Control燦etwork

In this paper, we propose a intrusion detection algorithm based on auto-encoder and three-way decisions (AE-3WD) for industrial control networks, aiming at the security problem of industrial control network. The ideology of deep learning is similar to the idea of intrusion detection. Deep learning is a kind of intelligent algorithm and has the ability of automatically learning. It uses self-learning to enhance the experience and dynamic classification capabilities. We use deep learning to improve the intrusion detection rate and reduce the false alarm rate through learning, a denoising AutoEncoder and three-way decisions intrusion detection method AE-3WD is proposed to improve intrusion detection accuracy. In the processing, deep learning AutoEncoder is used to extract the features of high-dimensional data by combining the coefficient penalty and reconstruction loss function of the encode layer during the training mode. A multi-feature space can be constructed by multiple feature extractions from AutoEncoder, and then a decision for intrusion behavior or normal behavior is made by three-way decisions. NSL-KDD data sets are used to the experiments. The experiment results prove that our proposed method can extract meaningful features and effectively improve the performance of intrusion detection.

High Camouflage Intrusion Detection Method for Structured Database Based on Multi Pattern Matching

with the rise and rapid development of mobile communication, intelligent terminal and data system, we are entering the era of mobile Internet. In recent years, more and more data need to be processed and transmitted in daily life, and structured data is becoming more and more important. Among them, multi-mode matching technology can search data in a wider range. Matching for multiple patterns at a time avoids unnecessary matching, accelerates the matching process, and helps to find longer matching information and obtain higher accuracy. This paper mainly introduces the high camouflage intrusion detection method of structured database based on multi-mode matching. This paper uses the high disguised intrusion detection method of structured database based on multi-mode matching, collects sensitive information of wireless access points and stations through the communication of WLAN in multimodal matching, then intercepts and forges data packets to initiate replay attack. Replay attack is characterized by abnormal traffic in the network, which can be detected by statistical analysis. The experimental results show that the high camouflage intrusion detection method based on multi-mode matching makes the camouflage intrusion detection rate increase by 23%. The limitations of the design and research of camouflage intrusion detection are analyzed, discussed and summarized, so as to enrich the academic research results.

Anonymization of Network Traces Data through Condensation-based Differential Privacy

Network traces are considered a primary source of information to researchers, who use them to investigate research problems such as identifying user behavior, analyzing network hierarchy, maintaining network security, classifying packet flows, and much more. However, most organizations are reluctant to share their data with a third party or the public due to privacy concerns. Therefore, data anonymization prior to sharing becomes a convenient solution to both organizations and researchers. Although several anonymization algorithms are available, few of them allow sufficient privacy (organization need), acceptable data utility (researcher need), and efficient data analysis at the same time. This article introduces a condensation-based differential privacy anonymization approach that achieves an improved tradeoff between privacy and utility compared to existing techniques and produces anonymized network trace data that can be shared publicly without lowering its utility value. Our solution also does not incur extra computation overhead for the data analyzer. A prototype system has been implemented, and experiments have shown that the proposed approach preserves privacy and allows data analysis without revealing the original data even when injection attacks are launched against it. When anonymized datasets are given as input to graph-based intrusion detection techniques, they yield almost identical intrusion detection rates as the original datasets with only a negligible impact.

Security assessment for routing-based synthesis on cyberphysical MEDA-based digital microfluidic biochip

Cyberphysical microelectrode-dot-array (CP-MEDA)-based digital microfluidic biochip (DMFB) is attracting more attention than its predecessor of traditional DMFB. Conventional DMFBs are mostly unable to recover from the errors incurred at assay run time, and thus, it leads to unacceptable results. Recent studies have revealed the vulnerability of CP-DFMBs to detect malicious intrusions during its design or operational phase. In this paper, we have analysed such vulnerable scenarios that have been utilized by the routing-based-synthesis approach on a CP-MEDA. We have also depicted the mixing operations based on routing for ensuring better security measures. Various attacking scenarios have been demonstrated on a MEDA-based DMFB, and moreover, checkpoint-based intrusion detection method has been proposed for the RBS technique. The effectiveness of our approach is compared with the available benchmark assays. Our proposed method has shown significant improvement over the existing state-of-the-art procedures in terms of assay execution time and intrusion detection rate.

Network Intrusion Detection Methods Based on Deep Learning

To detect network attacks more effectively, this study uses Honeypot techniques to collect the latest network attack data and proposes network intrusion detection classification models, based on deep learning, combined with DNN and LSTM models. Experiments showed that the data set training models gave better results than the KDD CUP 99 training model’s detection rate and false positive rate. The DNN-LSTM intrusion detection algorithm, proposed in this study, gives better results than KDD CUP 99 training model. Compared to other algorithms, such as LeNet, DNNLSTM intrusion detection algorithm exhibits shorter classification test time along with better accuracy and recall rate of intrusion detection.

An Integrated Model for Monitoring Nodes in Computer Networks

Monitoring complex computer network environment is now a very challenging task for network administrators despite the various existing monitoring applications for networks that are faced with the issues of centralized monitoring, which causes network traffic, reduces network bandwidth, and are unable to concurrently run two or more network services. This research paper was designed to tackle the problems exhibited by the existing network monitoring application by integrating different network monitoring services in a single model using the power of agent’s distributed processing and monitoring services. Data about the existing and proposed model was gathered using key informant interview approach, and observation of the existing software. Iterative software model was adopted as the software development life cycle based on its strengths and suitability. The proposed model was developed using use-case and sequence diagrams. Suitable programming languages and development environment such as Java, JavaScript, Hypertext Preprocessor, Hypertext markup language and MySQL were used in coding the software prototype. The functionality of the proposed system was tested and results showed that the proposed system has 100% anomaly network intrusion detection rate and better functional features as compared to the existing network monitoring applications observed.

A Novel Technique for IDS in Distributed Data Environment Using Merkel Based Security Mechanism for Secure User Allocation

Multiple corporations and people frequently launching their data in the cloud environment. With the huge growth of data mining and the cloud storage paradigm without checking protection policies and procedures that can pose a great risk to their sector. The data backup in the cloud storage would not only be problematic for the cloud user but also the Cloud Service Provider (CSP). The unencrypted handling of confidential data is likely to make access simpler for unauthorized individuals and also by the CSP. Normal encryption algorithms need more primitive computing, space and costs for storage. It is also of utmost importance to secure cloud data with limited measurement and storage capacity. Till now, different methods and frameworks to maintain a degree of protection that meets the requirements of modern life have been created. Within those systems, Intrusion Detection Systems (IDS) appear to find suspicious actions or events which are vulnerable to a system's proper activity. Today, because of the intermittent rise in network traffic, the IDS face problems for detecting attacks in broad streams of links. In existing the Two-Stage Ensemble Classifier for IDS (TSE-IDS) had been implemented. For detecting trends on big data, the irrelevant data characteristics appear to decrease both the velocity of attack detection and accuracy. The computing resource available for training and testing of the IDS models is also increased. We have put forward a novel strategy in this research paper to the above issues to improve the balance of the server load effectively with protected user allocation to a server, and thereby minimize resource complexity on the cloud data storage device, by integrating the Authentication based User-Allocation with Merkle based Hashing-Tree (AUA-MHT) technique. Through this, the authentication attack and flood attack are detected and restrict unauthorized users. By this proposed model the cloud server verifies, by resolving such attacks, that only approved users are accessing the cloud info. The proposed framework AUA-MHT performs better than the existing model TSE-IDS for parameters such as User Allocation Rate, Intrusion Detection Rate and Space Complexity

A Novel QoS Based Secure Unequal Clustering Protocol with Intrusion Detection System in Wireless Sensor Networks

Wireless sensor network (WSN) becomes a hot research topic owing to its application in different fields. Minimizing the energy dissipation, maximizing the network lifetime, and security are considered as the major quality of service (QoS) factors in the design of WSN. Clustering is a commonly employed energy-efficient technique; however, it results in a hot spot issue. This paper develops a novel secure unequal clustering protocol with intrusion detection technique to achieve QoS parameters like energy, lifetime, and security. Initially, the proposed model uses adaptive neuro fuzzy based clustering technique to select the tentative cluster heads (TCHs) using three input parameters such as residual energy, distance to base station (BS), and distance to neighbors. Then, the TCHs compete for final CHs and the optimal CHs are selected using the deer hunting optimization (DHO) algorithm. The DHO based clustering technique derives a fitness function using residual energy, distance to BS, node degree, node centrality, and link quality. To further improve the performance of the proposed method, the cluster maintenance phase is utilized for load balancing. Finally, to achieve security in cluster based WSN, an effective intrusion detection system using a deep belief network is executed on the CHs to identify the presence of intruders in the network. An extensive set of experiments were performed to ensure the superior performance of the proposed method interms of energy efficiency, network lifetime, packet delivery ratio, average delay, and intrusion detection rate.

A deep learning- based frechet and dirichlet model for intrusion detection in IWSN

Industrial Wireless Sensor Network (IWSN) includes numerous sensor nodes that collect data about target objects and transmit to sink nodes (SN). During data transmission among nodes, intrusion detection is carried to improve data security and privacy. Intrusion detection system (IDS) examines the network for intrusions based on user activities. Several works have been done in the field of intrusion detection and different measures are carried out to increase data security from the issues related to black hole, Sybil attack, Worm hole, identity replication attack and etc. In various existing approaches, secure data transmission is not achieved, therefore resulted in compromising the security and privacy of IWSNs. Accurate intrusion detection is still challenging task in terms of improving security and intrusion detection rate. In order to improve intrusion detection rate (IDR) with minimum time, generalized Frechet Hyperbolic Deep and Dirichlet Secured (FHD-DS) data communication model is introduced. At first, Frechet Hyperbolic Deep Traffic (FHDT) feature extraction method is designed to extract more relevant network activities and inherent traffic features. With the help of extracted features, anomalous or normal data is predicted. Followed by Statistical Dirichlet Anomaly-based Intrusion Detection model is applied to discover intrusion. Here, Dirichlet distribution is evaluated to attain secure data transmission and significantly detect intrusions in WSNs. Experimental evaluation is carried out with KDD cup 99 dataset on factors such as IDR, intrusion detection time (IDT) and data delivery rate (DDR). The observed results show that the generalized FHD-DS data communication method achieves higher IDR with minimum time.

Research on hybrid intrusion detection method based on the ADASYN and ID3 algorithms.

Intrusion detection system plays an important role in network security. Early detection of the potential attacks can prevent the further network intrusion from adversaries. To improve the effectiveness of the intrusion detection rate, this paper proposes a hybrid intrusion detection method that utilizes ADASYN (Adaptive Synthetic) and the decision tree based on ID3 algorithm. At first, the intrusion detection dataset is transformed by coding technology and normalized. Subsequently, the ADASYN algorithm is applied to implement oversampling on the training set, and the ID3 algorithm is employed to build a decision tree model. In addition, the model proposed by the research is evaluated by accuracy, precision, recall, and false alarm rate. Besides, a performance comparison is conducted with other models. Consequently, it is found that the combined model based on ADASYN and ID3 decision tree proposed in this research possesses higher accuracy as well as lower false alarm rate, which is more suitable for intrusion detection tasks.

RNNIDS: Enhancing network intrusion detection systems through deep learning

Security of information passing through the Internet is threatened by today’s most advanced malware ranging from orchestrated botnets to simpler polymorphic worms. These threats, as examples of zero-day attacks, are able to change their behavior several times in the early phases of their existence to bypass the network intrusion detection systems (NIDS). In fact, even well-designed, and frequently-updated signature-based NIDS cannot detect the zero-day treats due to the lack of an adequate signature database, adaptive to intelligent attacks on the Internet. More importantly, having an NIDS, it should be tested on malicious traffic dataset that not only represents known attacks, but also can to some extent reflect the characteristics of unknown, zero-day attacks. Generating such traffic is identified in the literature as one of the main obstacles for evaluating the effectiveness of NIDS. To address these issues, we introduce RNNIDS that applies Recurrent Neural Networks (RNNs) to find complex patterns in attacks and generate similar ones. In this regard, for the first time, we demonstrate that RNNs are helpful to generate new, unseen mutants of attacks as well as synthetic signatures from the most advanced malware to improve the intrusion detection rate. Besides, to further enhance the design of an NIDS, RNNs can be employed to generate malicious datasets containing, e.g., unseen mutants of a malware. To evaluate the feasibility of our approaches, we conduct extensive experiments by incorporating publicly available datasets, where we show a considerable improvement in the detection rate of an off-the-shelf NIDS (up to 16.67%).

The Effects of Facial Expressions on Face Biometric System’s Reliability

The human mood has a temporary effect on the face shape due to the movement of its muscles. Happiness, sadness, fear, anger, and other emotional conditions may affect the face biometric system’s reliability. Most of the current studies on facial expressions are concerned about the accuracy of classifying the subjects based on their expressions. This study investigated the effect of facial expressions on the reliability of a face biometric system to find out which facial expression puts the biometric system at greater risk. Moreover, it identified a set of facial features that have the lowest facial deformation caused by facial expressions to be generalized during the recognition process, regardless of which facial expression is presented. In order to achieve the goal of this study, an analysis of 22 facial features between the normal face and six universal facial expressions is obtained. The results show that the face biometric systems are affected by facial expressions where the disgust expression achieved the most dissimilar score, while the sad expression achieved the lowest dissimilar score. Additionally, the study identified the five and top ten facial features that have the lowest facial deformations on the face shape in all facial expressions. Besides that, the relativity score showed less variances between the sample using the top facial features. The obtained results of this study minimized the false rejection rate in the face biometric system and subsequently the ability to raise the system’s acceptance threshold to maximize the intrusion detection rate without affecting the user convenience.

Performance analysis of optimal cluster selection and intrusion detection by hierarchical K-means clustering with hybrid ABC-DT

PurposeThis paper aims to propose a multi-dimensional hierarchical K-means clustering algorithm for the purpose of intrusion detection. Initially, the clustering set of rules is proposed to shape some of clusters in the network and then the most beneficial clusters are decided on by the use of Cuckoo search optimization set of rules. Finally, an Artificial Bee Colony primarily based selection tree (ABC-DT) classifier is rented to classify the regular and unusual instances present in the network with the aid of the extracted features.Design/methodology/approachIntrusion detection system (IDS) is crucial for the network system; the intruder can take sensitive details about the network. IDS are said to be more effective when it has both high intrusion detection rate and low false alarm rate. Numerous strategies including gadget mastering, records mining and statistical techniques were tested for IDS mission. Recent study reveals that combining multiple classifiers, i.e. classifiers ensemble, can also own better performance than unmarried classifier. In this paper, a comparative study is conducted of the overall performance of four classifiers, i.e. hybrid ABC-DT particle swarm optimization-based K-means clustering (PSO-KM), help vector device (SVM) and K-Nearest neighbour (KNN). All the four classifiers are tested with exceptional packet sizes 1470, 1024, 512 and 256. The experiment is carried out for the speed ranging from turned into done for the velocity ranging from 250Mbps, 500Mbps, 750Mbps, 1.0Gpbs, 1.5Gbps, and 2.0Gbps in terms of accuracy, detection charge, specificity, false alarm charge and computational time. The experimental results reveals that the hybridization of classifiers performs better than the base classifiers in all scenarios.FindingsThis study analyses the performance of hybrid ABC-DT classifier and compares the performance against three well-known classifiers such as PSO-KM, SVM and K-NN. The performances of all the four classifiers are tested with Discovery in Data Mining (KDD) CUP 99 dataset with different packet sizes 1470, 1024, 512 and 256. The results show the classifier performance variations with different speed ranges. From the experimental results and analysis, the hybridization of classifiers such as ABC-DT outperforms the base classifiers in all scenarios.Originality/valueThe novel approach in this paper is used to study the hybrid ABC-DT classifier and compare the performance against three well-known classifiers such as PSO-KM, SVM and K-NN. The discussed concept is used within the network to monitor the traffic to and from all the devices connected in that network.

A Smart Grid AMI Intrusion Detection Strategy Based on Extreme Learning Machine

The smart grid is vulnerable to network attacks, thus requiring a high detection rate and fast detection speed for intrusion detection systems. With a fast training speed and a strong model generalization ability, the extreme learning machine (ELM) perfectly meets the needs of intrusion detection of the smart grid. In this paper, the ELM is applied to the field of smart grid intrusion detection. Aiming at the problem that the randomness of input weights and hidden layer bias in the ELM cannot guarantee the optimal performance of the ELM intrusion detection model, a genetic algorithm (GA)-ELM algorithm based on a genetic algorithm (GA) is proposed. GA is used to optimize the input weight and hidden layer bias of the ELM. Firstly, the input weight and hidden layer bias of the ELM are mapped to the chromosome vector of a GA, and the test error of the ELM model is set as the fitness function of the GA. Then, the parameters of the ELM intrusion detection model are optimized by genetic operation; the input weight and bias, corresponding to the minimum test error, are selected to improve the performance of the ELM model. Compared with the ELM and online sequential extreme learning machine (OS-ELM), the GA-ELM effectively improves the accuracy, detection rate and precision of intrusion detection and reduces the false positive rate and missing report rate.

Application of artificial fish swarm optimization semi-supervised kernel fuzzy clustering algorithm in network intrusion

For the unsupervised learning based clustering algorithm, the intrusion detection rate is low, and the training sample based on supervised learning clustering algorithm is insufficient. A semi-supervised kernel fuzzy C-means clustering algorithm based on artificial fish swarm optimization (AFSA-KFCM) is proposed. Firstly, the kernel function is used to change the distance function in the traditional semi-supervised fuzzy C-means clustering algorithm to define a new objective function, thus improving the probabilistic constraints of the fuzzy C-means algorithm. Then, the artificial fish swarm algorithm with strong global optimization ability is used to improve the KFCM sensitivity to the initial cluster center and easy to fall into the local extremum, thus improving the convergence speed and improving the classification effect. The test results in the Wine and IRIS public datasets show that the AFSA-KFCM clustering algorithm is superior to the traditional algorithm in clustering accuracy and time efficiency. At the same time, the experimental results in KDDCUP99 experimental data show that the algorithm can obtain the ideal detection rate and false detection rate in intrusion detection.

Intelligent intrusion detection system in smart grid using computational intelligence and machine learning

AbstractSmart grid systems enhanced the capability of traditional power networks while being vulnerable to different types of cyber‐attacks. These vulnerabilities could cause attackers to crash into the network breaching the integrity and confidentiality of the smart grid systems. Therefore, an intrusion detection system (IDS) becomes an important way to provide a secure and reliable services in a smart grid environment. This article proposes a feature‐based IDS for smart grid systems. The proposed system performance is evaluated in terms of accuracy, intrusion detection rate (DR), and false alarm rate (FAR). The obtained results show that the random forest and neural network classifiers have outperformed other classifiers. We have achieved a 0.5% FAR on KDD99 dataset and a 0.08% FAR on the NSLKDD dataset. The DR and the testing accuracy on average are 99% for both datasets.