Kinds Of Attacks Research Articles

Influential Node Identification of Network Based on Agglomeration Operation

Networks with distinct topological structures varies in the ability to resist different kinds of attacks. Node protection in terms of node importance is an effective way to ensure the reliable communication of networks. Thus, the protection of influential node detected by node importance evaluation is beneficial to strengthen the invulnerability and robustness of networks. In this work, the network agglomeration method based on node contraction is utilized to evaluate the influence of nodes and identify important nodes in five kinds of interconnection networks. We show that the agglomeration method, which takes both the degree and position into account, is valid and feasible for these five interconnection networks.

Deep-Learning Based Detection for Cyber-Attacks in IoT Networks: A Distributed Attack Detection Framework

The widespread use of smart devices and the numerous security weaknesses of networks has dramatically increased the number of cyber-attacks in the internet of things (IoT). Detecting and classifying malicious traffic is key to ensure the security of those systems. This paper implements a distributed framework based on deep learning (DL) to prevent many different sources of vulnerability at once, all under the same protection system. Two different DL models are evaluated: feed forward neural network and long short-term memory. The models are evaluated with two different datasets (i.e.NSL-KDD and BoT-IoT) in terms of performance and identification of different kinds of attacks. The results demonstrate that the proposed distributed framework is effective in the detection of several types of cyber-attacks, achieving an accuracy up to 99.95% across the different setups.

Intelligent Physical Attack Against Mobile Robots With Obstacle-Avoidance

The security issue of mobile robots has attracted considerable attention in recent years. In this article, we propose an intelligent physical attack to trap mobile robots into a preset position by learning the obstacle-avoidance mechanism from external observation. The salient novelty of our work lies in revealing the possibility that physical-based attacks with intelligent and advanced design can present real threats while without prior knowledge of the system dynamics or access to the internal system. This kind of attack cannot be handled by countermeasures in traditional cyberspace security. To practice, the cornerstone of the proposed attack is to actively explore the complex interaction characteristic of the victim robot with the environment and learn the obstacle-avoidance knowledge exhibited in the limited observations of its behaviors. Then, we propose shortest-path and hands-off attack algorithms to find efficient attack paths from the tremendous motion space, achieving the driving-to-trap goal with low costs in terms of path length and activity period, respectively. The convergence of the algorithms is proved and the attack performance bounds are further derived. Extensive simulations and real-life experiments illustrate the effectiveness of the proposed attack, beckoning future investigation for the new physical threats and defense on robotic systems.

A Literature Review of Blockchain Applications in Healthcare

Abstract: Health data is usually in a scattered manner as they are usually gathered by various entities. The data’s scatteredness develops a burden in designing adequate health bills which ensure the well-being of the patients. Moreover, the concerns in achieving synchronization and instantaneous access to such data worsens the problem all the more. So, designing a system that can ensure the integrity, security, preciseness, and accessibility of the patient’s medical data is of paramount importance. Health systems based on blockchain can guarantee the above features and protect data from being tampered or from any kind of attacks. Blockchain also helps in management of data and its flawless integration. It makes most of its smart contracts feature to execute the several requests and queries related to the patients (medicine, appointments, medical procedures, lab tests or previous medical information). All the stakeholders in the system should be able to obtain the medical data preserved in a database not having to compromise on its credibility. In this survey, we examine the previous research work various authors have carried out on implementing blockchain in several aspects of healthcare.

A two stage hybrid intrusion detection using genetic algorithm in IoT networks

Today, almost 90% of the technology in usage is linked with IoT (Internet of Things). which brings the question, what is IoT? Internet of things is a system of co-related computers, electronic devices, and objects. IoT essentially controls almost every online service which we avail without human -to-human interaction. An IDS is a hardware or software system that automatically monitors, identifies, and alerts a computer or network against attacks and intrusions. The proposed hybrid model makes use of genetic algorithm with UNSW NB-15 dataset which contains multiple classes of attack to provide a huge variety of attacks which will help to simulate different kinds of attack which will help train the model better. We have used CNN and LSTM model for extracting features. By detecting the attacks quickly, we can identify potential intruders and limit the damage. Feature selection and classification have been performed using Generic algorithm. This hybrid model helps to check whether the alert is an attack or not, if yes what kind of attack is it. the proposed Hybrid model works better than a conventional intrusion detection system, we got 99.38% accuracy from this model.

Detection of DDoS attack in IoT traffic using ensemble machine learning techniques

<abstract><p>A denial-of-service (DoS) attack aims to exhaust the resources of the victim by sending attack packets and ultimately stop the legitimate packets by various techniques. The paper discusses the consequences of distributed denial-of-service (DDoS) attacks in various application areas of Internet of Things (IoT). In this paper, we have analyzed the performance of machine learning(ML)-based classifiers including bagging and boosting techniques for the binary classification of attack traffic. For the analysis, we have used the benchmark CICDDoS2019 dataset which deals with DDoS attacks based on User Datagram Protocol (UDP) and Transmission Control Protocol (TCP) in order to study new kinds of attacks. Since these protocols are widely used for communication in IoT networks, this data has been used for studying DDoS attacks in the IoT domain. Since the data is highly unbalanced, class balancing is done using an ensemble sampling approach comprising random under-sampler and ADAptive SYNthetic (ADASYN) oversampling technique. Feature selection is achieved using two methods, i.e., (a) Pearson correlation coefficient and (b) Extra Tree classifier. Further, performance is evaluated for ML classifiers viz. Random Forest (RF), Naïve Bayes (NB), support vector machine (SVM), AdaBoost, eXtreme Gradient Boosting (XGBoost) and Gradient Boosting (GB) algorithms. It is found that RF has given the best performance with the least training and prediction time. Further, it is found that feature selection using extra trees classifier is more efficient as compared to the Pearson correlation coefficient method in terms of total time required in training and prediction for most classifiers. It is found that RF has given best performance with least time along with feature selection using Pearson correlation coefficient in attack detection.</p></abstract>

Ontology for Blind SQL Injection

In cyberspace, there exists a prevalent problem that heavily occurs to web application databases and that is the exploitation of websites by using SQL injection attacks. This kind of attack becomes more difficult when it comes to blind SQL vulnerabilities. In this paper, we will first make use of this vulnerability, and subsequently, we will build an ontology (OBSQL) to address the detection of the blind SQL weakness. Therefore, to achieve the exploitation, we reproduce the attacks against a website in production mode. We primarily detect the presence of the vulnerability, after we use our tools to abuse it. Last but not least, we prove the importance of applying ontology in cybersecurity for this matter. The mitigation techniques in our ontology will be addressed in our future work.

Enhanced Security with Improved Defensive Routing Mechanism in Wireless Sensor Networks

In recent scenario of Wireless Sensor Networks (WSNs), there are many application developed for handling sensitive and private data such as military information, surveillance data, tracking, etc. Hence, the sensor nodes of WSNs are distributed in an intimidating region, which is non-rigid to attacks. The recent research domains of WSN deal with models to handle the WSN communications against malicious attacks and threats. In traditional models, the solution has been made for defending the networks, only to specific attacks. However, in real-time applications, the kind of attack that is launched by the adversary is not known. Additionally, on developing a security mechanism for WSN, the resource constraints of sensor nodes are also to be considered. With that note, this paper presents an Enhanced Security Model with Improved Defensive Routing Mechanism (IDRM) for defending the sensor network from various attacks. Moreover, for efficient model design, the work includes the part of feature evaluation of some general attacks of WSNs. The IDRM also includes determination of optimal secure paths and Node security for secure routing operations. The performance of the proposed model is evaluated with respect to several factors; it is found that the model has achieved better security levels and is efficient than other existing models in WSN communications. It is proven that the proposed IDRM produces 74% of PDR in average and a minimized packet drop of 38% when comparing with the existing works.

An Improved Two-Factor Authentication Scheme for Healthcare System

Patients can communicate with their doctors from the comfort of their own homes. The Telecare Medicine Information Service is one of the most efficient, secure, and protective forms of communication. It maintains and provides patients' Electronic Medical Records (EMR), allowing doctors to track their patients and ensure they receive correct healthcare services. Therefore, the key concerns to stop unauthorised users from obtaining health information are security and privacy. There are several authentication methods in use today, but they are all susceptible to different kinds of attacks. We enhanced a two-factor-based authentication technique to increase security and privacy while addressing earlier shortcomings. We simulate our proposed scheme using the Automated Validation of Internet Security Protocols and Applications tool (AVISPA) tool that confirms that scheme is secure against active and passive attacks including replay and man-in-the-middle attacks. Our proposed protocol provides high security and better complexity based on communication, computation costs and execution time.

Occluded Person Re-Identification via Defending Against Attacks From Obstacles

Due to incomplete appearance features, the identity matching of occluded pedestrians under multiple cross-camera views is a long-term challenge. Although existing re-identification (re-ID) solutions of occluded pedestrians have made significant progress, most of them achieve accurate identity matching by extracting pedestrian appearance features from unoccluded areas. However, when a pedestrian is partially blocked by the body of another pedestrian, existing methods cannot accurately determine whether the unoccluded body parts belong to the target pedestrian, which brings great difficulties to pedestrian identity matching. To alleviate this problem, this paper introduces the idea of adversarial attack into occluded person re-ID and proposes an adversarial training framework that can defend against attacks from obstacles to resist the interference of obstacles on pedestrian identity matching. Unlike existing solutions, the proposed framework is not limited to extracting features of unoccluded human body areas to achieve occluded person re-ID, but explores how to make the re-ID model more resistant to obstacles. In the proposed framework, the occluded pedestrian images are regarded as adversarial examples and used to attack model training. If the trained model can defend against this kind of attack, its generalization is significantly improved, and the above-mentioned issues are also effectively solved. Specifically, a single-branch dual-stream collaborative network is designed. With the cooperation of the pre-trained verification guidance network, the model realizes the attack and defense of adversarial samples. This work broadens research horizons in robust model design of occluded person re-ID, and expands the scope of adversarial attacks. Compared with existing solutions, a lot of experimental results confirm that the proposed solution achieves better performance on two occluded re-ID datasets and two partial re-ID datasets.

An Intelligent Intrusion Detection System in Smart Grid Using PRNN Classifier

Typically, smart grid systems enhance the ability of conventional power system networks as it is vulnerable to several kinds of attacks. These vulnerabilities might cause the attackers or intruders to collapse the entire network system thus breaching the confidentiality and integrity of smart grid systems. Thus, for this purpose, Intrusion detection system (IDS) plays a pivotal part in offering a reliable and secured range of services in the smart grid framework. Several existing approaches are there to detect the intrusions in smart grid framework, however they are utilizing an old dataset to detect anomaly thus resulting in reduced rate of detection accuracy in real-time and huge data sources. So as to overcome these limitations, the proposed technique is presented which employs both real-time raw data from the smart grid network and KDD99 dataset thus detecting anomalies in the smart grid network. In the grid side data acquisition, the power transmitted to the grid is checked and enhanced in terms of power quality by eradicating distortion in transmission lines. In this approach, power quality in the smart grid network is enhanced by rectifying the fault using a FACT device termed UPQC (Unified Power Quality Controller) and thereby storing the data in cloud storage. The data from smart grid cloud storage and KDD99 are pre-processed and are optimized using Improved Aquila Swarm Optimization (IASO) to extract optimal features. The probabilistic Recurrent Neural Network (PRNN) classifier is then employed for the prediction and classification of intrusions. At last, the performance is estimated and the outcomes are projected in terms of grid voltage, grid current, Total Harmonic Distortion (THD), voltage sag/swell, accuracy, precision, recall, F-score, false acceptance rate (FAR), and detection rate of the classifier. The analysis is compared with existing techniques to validate the proposed model efficiency.

Confidential High-Performance Computing in the Public Cloud

High-performance computing (HPC) in the public cloud democratizes the supercomputing power that most users cannot afford to purchase and maintain. Researchers have studied its viability, performance, and usability. However, HPC in the cloud has a unique feature—users have to export data and computation to somewhat untrusted cloud platforms. Users will either fully trust cloud providers to protect from all kinds of attacks or keep sensitive assets in-house instead. With the recent deployment of the trusted execution environment (TEE) in the cloud, confidential computing for HPC in the cloud is becoming practical for addressing users' privacy concerns. This article discusses the threat models, unique challenges, possible solutions, and significant gaps, focusing on TEE-based confidential HPC computing. We hope this discussion will improve the understanding of this new topic for HPC in the cloud and promote new research directions.

Real-Time Malicious Traffic Detection With Online Isolation Forest Over SD-WAN

Software Defined Network (SDN) has been widely used in modern network architecture. The SD-WAN is considered as a technology that has a potential to revolutionize the WAN service usage by utilizing the SDN philosophy. Attacking SDN router and controller can affect the network and block the entire services. In this paper, we propose a machine learning based anomalous traffic detection framework named OADSD over SD-WAN that can achieve task independent and has the ability of adapting to the environment. The OADSD adopts Distributed Dynamic Feature Extraction (DDFE) to extract representative features directly from the raw traffic, and proposes the On-demand Evolving Isolation Forest (OEIF) to make the system adapt to an environment. We provide a theoretical analysis of the performance of the OADSD. We also conduct comprehensive experiments to evaluate the performance of the OADSD with real world public datasets as well as a small real testbed. Our experiments under real world public datasets show that, the OADSD can accurately detect various kinds of attacks with a high performance. Compared with the state-of-the-art systems, the OADSD can achieve up to 60% accuracy improvement.

Optimal Fuzzy Logic Enabled Intrusion Detection for Secure IoT-Cloud燛nvironment

Recently, Internet of Things (IoT) devices have developed at a faster rate and utilization of devices gets considerably increased in day to day lives. Despite the benefits of IoT devices, security issues remain challenging owing to the fact that most devices do not include memory and computing resources essential for satisfactory security operation. Consequently, IoT devices are vulnerable to different kinds of attacks. A single attack on networking system/device could result in considerable data to data security and privacy. But the emergence of artificial intelligence (AI) techniques can be exploited for attack detection and classification in the IoT environment. In this view, this paper presents novel metaheuristics feature selection with fuzzy logic enabled intrusion detection system (MFSFL-IDS) in the IoT environment. The presented MFSFL-IDS approach purposes for recognizing the existence of intrusions and accomplish security in the IoT environment. To achieve this, the MFSFL-IDS model employs data pre-processing to transform the data into useful format. Besides, henry gas solubility optimization (HGSO) algorithm is applied as a feature selection approach to derive useful feature vectors. Moreover, adaptive neuro fuzzy inference system (ANFIS) technique was utilized for the recognition and classification of intrusions in the network. Finally, binary bat algorithm (BBA) is exploited for adjusting parameters involved in the ANFIS model. A comprehensive experimental validation of the MFSFL-IDS model is carried out using benchmark dataset and the outcomes are assessed under distinct aspects. The experimentation outcomes highlighted the superior performance of the MFSFL-IDS model over recent approaches with maximum accuracy of 99.80%.

An optimized Identification System by using Shark Smell algorithm for Biometric Images Crossing

The security and privacy fields and multimedia biometrics have been widely used today for personal authentication. Sclera and Palm-print of humans are one of the fastest, accurate, reliable, and secure biometric techniques for identification and verification based on unique features. The majority of the biometric systems are based on the global features, which may lead to weak performance in cases of poor-quality biometric images, therefore, swarm intelligence techniques are used to improve recognition accuracy, reliability, and quickness. In this paper, an enhancement shark smell optimization (ESSO) is proposed to build an efficient hybrid identification system depend on the sclera and palm-print images. The SIFT algorithm used to extract features from the biometric images. The optimal key-points from this feature are obtained using ESSO and chaotic map, and finally, generation digital signature using a 256-MD5 algorithm for each user. The Package of the NIST tests proves that the generated keys are random, unpredictable, uncorrelated, and robust against different kinds of attacks.

Design of Intrusion Detection System using Ensemble Learning Technique in Cloud Computing Environment

The key advantage of the cloud is that it fluidly propagates to fulfil changeable requirements and provides an environment that is repeatable and can be scaled down instantly when needed. Therefore, it is necessary to protect this cloud environment from malicious attacks such as spamming, keylogging, Denial of Service (DoS), and Distributed Denial of Service (DDoS). Among these kinds of attacks, DDoS has the capability to establish a high flood of malicious attacks on the cloud environment or Software Defined Networking (SDN) based cloud environment. Hence in this work, an ensemble based deep learning technique is proposed to detect attacks in cloud and SDN based cloud environments. Here, the ensemble model is formed by combining K-means with deep learning classifiers such as Long Short term Memory (LSTM) network, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU) and Deep Neural Network (DNN). Initially, preprocessing with data cleaning and standardization is applied to the input data. Meanwhile, a random forest is implemented for extracting the minimum significant features. After that, the proposed ensemble based approach is utilized for detecting the intrusion. This approach is used to enhance the performance of the deep learning classifiers without much computational complexity. This model is trained and evaluated using two datasets as CICIDS 2018 and SDN based DDOS attack datasets. The proposed approach provides better intrusion detection performance in terms of F1 measure, precision, accuracy, and recall. By using the proposed approach, the accuracy and precision value attained is 99.685 and 0.992, respectively.

Cyber Attack Detection in Wireless Adhoc Network using Artificial Intelligence

A wireless sensor network, also known as a WSN, is made up of thousands of minuscule sensor nodes that are connected to one another in order to monitor, track, and organize data collected in an unattended environment in the most prominent location. Due to its one-of-a-kind qualities, it has, the wireless sensor network is gaining traction in a variety of sectors and put to use in a wide range of applications, including surveillance, healthcare, and industry. These networks exposed to a variety of security flaws and major threats because of their dynamic design and deployment in an unsupervised environment. Cybercriminals prey on individuals who utilize the internet as well as organizations in order to get sensitive information. The hackers were able to access critical data on the company's systems, such as login information, credit card details, and bank account numbers. Phishing attacks are a sort of cyberattack in which hackers trick internet users into believing their websites are authentic in order to collect the users' private information. The purpose of these attacks is to steal this information. Malware assaults begin with the covert installation of malicious software on corporate servers or user PCs via the use of the internet. The attackers then continue to steal every piece of information that kept on the targeted server or computer. Malware used in an ever-increasing number of attacks these days. An incursion into a network is a kind of attack in which the perpetrator seeks to take possession of all of the network's resources. Approaches based on heuristic analysis and visual resemblance used, regardless of whether they are blacklisted or whitelisted.

A Rule-Based Approach for Grey Hole Attack Prediction in Wireless Sensor Networks

The Wireless Sensor Networks (WSN) are vulnerable to assaults due to the fact that the devices connected to them have a reliable connection to the internet. A malicious node acts as the controller and uses a grey hole attack to get the data from all of the other nodes in the network. Additionally, the nodes are discarding and modifying the data packets according to the requirements of the system. The assault modifies the fundamental concept of the WSNs, which is that different devices should communicate with one another. In the proposed system, there is a fuzzy idea offered for the purpose of preventing the grey hole attack from making effective communication among the WSN devices. The currently available model is unable to recognise the myriad of different kinds of attacks. The fuzzy engine identified suspicious actions by utilising the rules that were generated to make a prediction about the malicious node that would halt the process. Experiments conducted using simulation are used to determine delay, accuracy, energy consumption, throughput, and the ratio of packets successfully delivered. It stands in contrast to the model that was suggested, as well as the methodologies that are currently being used, and analogue behavioural modelling. In comparison to the existing method, the proposed model achieves an accuracy rate of 45 percent, a packet delivery ratio of 79 percent, and a reduction in energy usage of around 35.6 percent. These results from the simulation demonstrate that the fuzzy grey detection technique that was presented has the potential to increase the network’s capability of detecting grey hole assaults.

Design of Intrusion Detection and Prevention Model Using COOT Optimization and Hybrid LSTM-KNN Classifier for MANET

INTRODUCTION: MANET is an emerging technology that has gained traction in a variety of applications due to its ability to analyze large amounts of data in a short period of time. Thus, these systems are facing a variety of security vulnerabilities and malware assaults. Therefore, it is essential to design an effective, proactive and accurate Intrusion Detection System (IDS) to mitigate these attacks present in the network. Most previous IDS faced challenges such as low detection accuracy, decreased efficiency in sensing novel forms of attacks, and a high false alarm rate. OBJECTIVES: To mitigate these concerns, the proposed model designed an efficient intrusion detection and prevention model using COOT optimization and a hybrid LSTM-KNN classifier for MANET to improve network security. METHODS: The proposed intrusion detection and prevention approach consist of four phases such as classifying normal node from attack node, predicting different types of attacks, finding the frequency of attack, and intrusion prevention mechanism. The initial phases are done through COOT optimization to find the optimal trust value for identifying attack nodes from normal nodes. In the second stage, a hybrid LSTM-KNN model is introduced for the detection of different kinds of attacks in the network. The third stage performs to classify the occurrence of attacks. RESULTS: The final stage is intended to limit the number of attack nodes present in the system. The proposed method's effectiveness is validated by some metrics, which achieved 96 per cent accuracy, 98 per cent specificity, and 35 seconds of execution time. CONCLUSION: This experimental analysis reveals that the proposed security approach effectively mitigates the malicious attack in MANET.

Intelligent Deep Learning for Anomaly-Based Intrusion Detection in IoT Smart Home Networks

The Internet of Things (IoT) is a tremendous network based on connected smart devices. These networks sense and transmit data by using advanced communication standards and technologies. The smart home is one of the areas of IoT networks, where home appliances are connected to the internet and smart grids. However, these networks are at high risk in terms of security violations. Different kinds of attacks have been conducted on these networks where the user lost their data. Intrusion detection systems (IDSs) are used to detect and prevent cyberattacks. These systems are based on machine and deep learning techniques and still suffer from fitting or overfitting issues. This paper proposes a novel solution for anomaly-based intrusion detection for smart home networks. The proposed model addresses overfitting/underfitting issues and ensures high performance in terms of hybridization. The proposed solution uses feature selection and hyperparameter tuning and was tested with an existing dataset. The experimental results indicated a significant increase in performance while minimizing misclassification and other limitations as compared to state-of-the-art solutions.