A Secure Service Discovery Scheme for Mobile ad hoc Network using Artificial Deep Neural Network

Web services are the new paradigm for distributed computing. They offer interoperability of application and integration of large scale distributed systems. Amongst the web service standards, service registry is crucial to the overall utility of web service technology. However, the web services discovery mechanism pertaining with the UDDI [1] registry is inefficient because it only supports keyword-based and category-based matching, leading to irrelevant matches. Therefore, the provision of the scalable, flexible and robust web services publication and discovery system is crucial for the overall utility of web services. In this paper, we develop a scalable, robust and efficient infrastructure for web services publication and discovery amongst domain-based registries. More importantly, a novel algorithm is provided to classify web services into domain-based registries based on their semantic description. Experimental results show that our approach outperforms a centralized approach in terms of service discovery time.

The Internet of things (IoT) is widely used to implement different applications like smart home, smart health care, smart city, and smart farming system. The development of large smart devices/sensors enables smart technologies making it possible to implement the smart application in real time. The IoT system has security challenges like authentication, data privacy, access control, and intrusion detection system. Similarly, the computation of the sensed information from the environment is a challenging task. The computation must perform using distributed or decentralized architecture to overcome the centralized system difficulty. In a distributed/decentralized system when multiple nodes participate in a computational process, there is the risk of mutual consensus problem, malicious node detection, or data modification attacks. In this paper, the authors have identified machine learning as a solution to address some of the existing security and computational challenges. The paper also explained the implementation platform available for the integration of IoT with machine learning.KeywordsSecurityComputationMachine learningSecure communicationIoT

Semantic Web services is considered as the concept bringing the web to its full potential by combining the best features of web services, agent technology, grid and the Semantic web. In this paper we present a semantic Web Services platform based on software agent (JASW), which introduces Semantic web and software agent and takes the automated discovery, selection, orchestration and invocation of Web services as application background. In the platform, we adopt Semantic web to accurately describe Web services, and use software agent to implement discovery, selection, and orchestration of Web services.

Service discovery mechanisms have continuously evolved during the last years to support the effective and efficient service composition in large-scale microservice applications. Still, the dynamic nature of services (and of their contexts) are being rarely taken into account for maximizing the desired quality of service. This paper proposes using machine learning techniques, as part of the service discovery process, to select microservice instances in a given context, maximize QoS, and take into account the continuous changes in the execution environment. Both deep neural networks and reinforcement learning techniques are used. Experimental results show how the proposed approach outperforms traditional service discovery mechanisms.

This chapter highlights the growing urgency for robust Intrusion Detection Systems (IDS) in the Internet of Things (IoT) security, focusing on sustainable cybersecurity strategies within the modern, highly interconnected digital ecosystem. As the rapid expansion of IoT devices presents vast attack surfaces, it is crucial to develop IDS that protect interconnected environments. This chapter performs a thorough analysis of IDS detection mechanisms and IoT security datasets, critically assessing the relevance and reliability. The evaluation emphasizes essential dataset attributes, including source authenticity, diversity, data volume, and real-world applicability. By systematically analyzing these criteria, the paper identifies datasets that offer comprehensive insights into IoT security's challenges, offering researchers a detailed resource for selecting datasets that align with the complexity of current IDS development. This review thus serves as a foundational guide for advancing IDS technology, aiming to foster more resilient and adaptive security solutions within the IoT landscape.

Intrusion Detection Systems (IDS) are vital for securing cloud environments, where dynamic scalability and distributed architecture present significant security challenges. Accurate, real-time threat detection with minimal false positives is essential for effective cloud protection. Traditional machine learning models such as Support Vector Machines (SVM) and Random Forests have been applied in IDS but often struggle with high false positive rates and limited effectiveness against novel or zero-day attacks. A deep neural network (DNN) architecture is designed, incorporating multiple ReLU-activated hidden layers and dropout layers to prevent overfitting. The model is trained using the Adam optimizer and categorical cross-entropy loss to ensure efficient learning and responsiveness. Evaluation on NSL-KDD and CICIDS2017 datasets demonstrates high detection accuracy—98.7% and 97.4% respectively—along with reduced false positive rates and promising results in identifying zero-day attacks during simulation. Future work includes integrating federated learning to support distributed deployment and enhance privacy preservation.

Cloud computing technology provides flexible, on-demand, and completely controlled computing resources and services are highly desirable. Despite this, with its distributed and dynamic nature and shortcomings in virtualization deployment, the cloud environment is exposed to a wide variety of cyber-attacks and security difficulties. The Intrusion Detection System (IDS) is a specialized security tool that network professionals use for the safety and security of the networks against attacks launched from various sources. DDoS attacks are becoming more frequent and powerful, and their attack pathways are continually changing, which requiring the development of new detection methods. Here the purpose of the study is to improve detection accuracy. Feature Selection (FS) is critical. At the same time, the IDS’s computational problem is limited by focusing on the most relevant elements, and its performance and accuracy increase. In this research work, the suggested Adaptive butterfly optimization algorithm (ABOA) framework is used to assess the effectiveness of a reduced feature subset during the feature selection phase, that was motivated by this motive Candidates. Accurate classification is not compromised by using an ABOA technique. The design of Deep Neural Networks (DNN) has simplified the categorization of network traffic into normal and DDoS threat traffic. DNN’s parameters can be fine-tuned to detect DDoS attacks better using specially built algorithms. Reduced reconstruction error, no exploding or vanishing gradients, and reduced network are all benefits of the changes outlined in this paper. When it comes to performance criteria like accuracy, precision, recall, and F1-Score are the performance measures that show the suggested architecture outperforms the other existing approaches. Hence the proposed ABOA + DNN is an excellent method for obtaining accurate predictions, with an improved accuracy rate of 99.05% compared to other existing approaches.

The dynamic yet vulnerable nature of an hoc network presents many new security and privacy challenges. Securing the process of service discovery is one of them. Novel solutions are therefore required. However, in order for appropriate security measures to be devised, all possible security threats must first be identified and thoroughly analysed. In this paper, we present a threat model for service discovery in ad hoc networks. Based on these threats, we proceed to derive the security services required to achieve secure service discovery.

Nowadays, along with network development, due to the threats of unknown sources, information communication is more vulnerable, and thus, more secured information is required. Intrusion Detection System (IDS) is very important for cybersecurity with the presence in particular of various networked computers' foundation. An efficient IDS apply machine learning method as computational technics to increase rates of detection to gain the high accuracy and low false alarms rate within the huge amounts of data. To increase the rate of detection, researcher usually implements the optimizer. Thus, in this research, a comprehensive experimental study is presented based on various binary to optimize the rate of detection and decrease the error. Moreover, Numerous researches have been conducted about intrusion detection systems with the old dataset such as Kddcup'99 dataset, and due to this reason, most of them did not get the potential accuracy to detect intrusion with the current intrusion as the old dataset is not covering the current attacks. Therefore, this research aims to A hybrid Anomaly Classification of IDS with Deep Learning (DL) and Binary Algorithms (BA) as Optimizer with the most updated dataset named "CICIDS2017" which can be used for the intrusion detection evaluation. Moreover, this research conducts the anomaly classification of IDS based on the deep neural network (DNN) as the Deep Learning (DL) platform and Binary Algorithms (BA) in terms of Binary Bat Algorithm (BBA), Binary Genetic Algorithm (BGA), Binary Gravitational Search Algorithm (BGSA) as optimizer to enhance the rates of detection. Some of the results which had been considered and achieved for DNN and the hybrid version (DNN and Binary Algorithms) are in terms of: Accuracy, Recall, Precision, Confusion Matrix, Sensitivity, Specificity, and Cost Error.

Intrusion detection system plays an important role in ensuring information security, and the key technology is to accurately identify various attacks in the network. Due to huge increase in network traffic and different types of attacks, accurately classifying the malicious and legitimate network traffic is time consuming and computational intensive. Recently, more and more researchers applied deep neural networks (DNNs) to solve intrusion detection problems. Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN), the two main types of DNN architectures, are widely explored to enhance the performance of intrusion detection system. In this paper, we made a systematic comparison of CNN and RNN on the deep learning based intrusion detection systems, aiming to give basic guidance for DNN selection.

Attacks on networks are currently the most pressing issue confronting modern society. Network risks affect all networks, from small to large. An intrusion detection system must be present for detecting and mitigating hostile attacks inside networks. Machine Learning and Deep Learning are currently used in several sectors, particularly the security of information, to design efficient intrusion detection systems. These systems can quickly and accurately identify threats. However, because malicious threats emerge and evolve regularly, networks need an advanced security solution. Hence, building an intrusion detection system that is both effective and intelligent is one of the most cognizant research issues. There are several public datasets available for research on intrusion detection. Because of the complexity of attacks and the continually evolving detection of an attack method, publicly available intrusion databases must be updated frequently. A convolutional recurrent neural network is employed in this study to construct a deep-learning-based hybrid intrusion detection system that detects attacks over a network. To boost the efficiency of the intrusion detection system and predictability, the convolutional neural network performs the convolution to collect local features, while a deep-layered recurrent neural network extracts the features in the proposed Hybrid Deep-Learning-Based Network Intrusion Detection System (HDLNIDS). Experiments are conducted using publicly accessible benchmark CICIDS-2018 data, to determine the effectiveness of the proposed system. The findings of the research demonstrate that the proposed HDLNIDS outperforms current intrusion detection approaches with an average accuracy of 98.90% in detecting malicious attacks.

Big data analytics (BDA) is a key technology that is used in a variety of corporate fields, including the welfare medical profession. In the actual world, there is no such thing as a flawless security solution for a certain activity or application.Technological growth has provided a variety of different ways over the years that may aid in the development of unique algorithms and techniques. The potential for cyberthreats and cyberattacks grows as more consumer and organizational information is digitized and collected for data analytics. Security and tactical information are two important areas where big data analytics is anticipated to make a substantial contribution. Current security problem and tracking systems (or SIEM) systems, which typically operate with a small selection of traditional data sources like firewalls, intrusion detection systems, etc., in a software system, do not adequately address security analytics in a big data context. The paper addressed the security challenges of big data analytics in social network platform. The paper also looked at the user engagement in different social media platforms.

The industry of telecommunications is being transformed towards 5G technology, because it has to deal with the emerging and existing use cases. Because, 5G wireless networks need rather large data rates and much higher coverage of the dense base station deployment with the bigger capacity, much better Quality of Service - QoS, and the need very low latency [1–3]. The provision of the needed services which are envisioned by 5G technologies need the new service models of deployment, networking architectures, processing technologies and storage to be defined. These technologies will cause the new problems for the cybersecurity of 5G systems and the security of their functionality. The developers and researchers working in this field make their best to secure 5G systems. The researchers showed that 5G systems have the security challenges. The researchers found the vulnerabilities in 5G systems which allow attackers to integrate malicious code into the system and make the different types of the illegitimate actions. MNmap, Battery drain attacks and MiTM can be successfully implemented on 5G. The paper makes the analysis of the existing cyber security problems in 5G technology. Based on the analysis, we suggest the novel Intrusion Detection System - IDS by means of the machine-learning algorithms. In the related papers the scientists offer to use NSL-KDD in order to train IDS. In our paper we offer to train IDS using the big datasets of DOS/DDOS attacks, besides of training using NSL-KDD. The research also offers the methodology of integration of the offered intrusion detection systems into an standard architecture of 5G. The paper also offers the pseudo code of the designed system.

The probability of network attacks is increasing daily due to the continuous development of tools and techniques that bypass the firewall and other network security boundaries. This motivates the researcher towards the upgradation and advancement in adaptive Artificial Intelligence (AI) based intrusion detection systems (IDS). The traditional machine learning (ML) based IDS has its limitations due to noise and the unexplainable nature of the decision‐making that took place during the implementation of the ML algorithm for categorization of attacked or normal data packets that arrive in the network. To address these issues, this research proposes an ML algorithm with the understanding of decisions through Explainable artificial intelligence (XAI). The dataset used for experimentation is IoTID20, which extracts data in a real‐time Internet of Things (IoT) environment. This paper compares the accuracy results of different ML algorithms such as Random Forest (RF), Extreme Gradient Boosting (XGBoost), Multilayer Perceptron –Neural Networks (MLP‐NN), Deep Neural Networks (DN), and Decision Tree (DT). During the classification of attacks, the Random Forest shows an accuracy of 93.80%, the XGBoost shows an accuracy of 97.30%, the Decision Tree shows an accuracy of 99.99%, the MLP Classifier—Neural Network shows an accuracy of 95.90%, and the Deep Neural Network (DNN) shows an accuracy of 94.60%. These algorithms are also analyzed with Precision, Recall, and F1‐Score. The proposed method of incorporating XAI increases the automation process with high accuracy and explainability of the decision to categorize anomalous and normal packets in an IoT environment. This remarkable achievement provides better intuitions in IDS with good protection in resistance to novel and unknown attacks.

Intrusion Detection Systems (IDS) are crucial for maintaining the security and integrity of network infrastructures. This review paper comprehensively examines the evolution and advancements in IDS technologies, focusing on both traditional methods and contemporary machine learning and deep learning approaches. Traditional IDS methods, including signature-based and anomaly-based detection, laid the groundwork for current systems but faced challenges such as high false-positive rates and limited adaptability. Recent advancements in machine learning, specifically supervised and unsupervised learning algorithms, have significantly enhanced the accuracy and efficiency of IDS. Deep learning techniques, particularly convolutional neural networks (CNNs) and recurrent neural networks (RNNs), offer promising solutions for complex and high-volume network traffic analysis. This review also explores federated learning for IDS, emphasizing its potential for data privacy preservation and reduced computational load. Furthermore, hybrid models combining various algorithms are discussed for their capability to leverage the strengths of multiple techniques. The paper synthesizes current research, highlighting key methodologies, datasets, evaluation metrics, and the future direction of IDS research. By providing a thorough analysis of existing literature and identifying gaps, this review aims to guide future research efforts and practical implementations in the field of network security.