The proliferation of IoT services has spurred a surge in network attacks, heightening cybersecurity concerns. Essential to network defense, intrusion detection and prevention systems (IDPSs) identify malicious activities, including denial of service (DoS), distributed denial of service (DDoS), botnet, brute force, infiltration, and Heartbleed. This study focuses on leveraging unsupervised learning for training detection models to counter these threats effectively. The proposed method utilizes basic autoencoders (bAEs) for dimensionality reduction and encompasses a three-stage detection model: one-class support vector machine (OCSVM) and deep autoencoder (dAE) attack detection, complemented by density-based spatial clustering of applications with noise (DBSCAN) for attack clustering. Accurately delineated clusters aid in mapping attack tactics. The MITRE ATT&CK framework establishes a “Cyber Threat Repository”, cataloging attacks and tactics, enabling immediate response based on priority. Leveraging preprocessed and unlabeled normal network traffic data, this approach enables the identification of novel attacks while mitigating the impact of imbalanced training data on model performance. The autoencoder method utilizes reconstruction error, OCSVM employs a kernel function to establish a hyperplane for anomaly detection, while DBSCAN employs a density-based approach to identify clusters, manage noise, accommodate diverse shapes, automatically determining cluster count, ensuring scalability, and minimizing false positives and false negatives. Evaluated on standard datasets such as CIC-IDS2017 and CSECIC-IDS2018, the proposed model outperforms existing state of art methods. Our approach achieves accuracies exceeding 98% for the two datasets, thus confirming its efficacy and effectiveness for application in efficient intrusion detection systems.

There can be many inherent issues in the process of managing cloud infrastructure and the platform of the cloud. The platform of the cloud manages cloud software and legality issues in making contracts. The platform also handles the process of managing cloud software services and legal contract-based segmentation. In this paper, we tackle these issues directly with some feasible solutions. For these constraints, the Averaged One-Dependence Estimators (AODE) classifier and the SELECT Applicable Only to Parallel Server (SELECT-APSL ASA) method are proposed to separate the data related to the place. ASA is made up of the AODE and SELECT Applicable Only to Parallel Server. The AODE classifier is used to separate the data from smart city data based on the hybrid data obfuscation technique. The data from the hybrid data obfuscation technique manages 50% of the raw data, and 50% of hospital data is masked using the proposed transmission. The analysis of energy consumption before the cryptosystem shows the total packet delivered by about 71.66% compared with existing algorithms. The analysis of energy consumption after cryptosystem assumption shows 47.34% consumption, compared to existing state-of-the-art algorithms. The average energy consumption before data obfuscation decreased by 2.47%, and the average energy consumption after data obfuscation was reduced by 9.90%. The analysis of the makespan time before data obfuscation decreased by 33.71%. Compared to existing state-of-the-art algorithms, the study of makespan time after data obfuscation decreased by 1.3%. These impressive results show the strength of our methodology.

A self-governing system consisting of mobile nodes that exchange information within a cellular area and is known as a mobile ad hoc network (MANET). Due to its dynamic nature, it is vulnerable to attacks and there is no fixed infrastructure. To transfer a data packet Ad-hoc On-Demand Distance Vector (AODV) is used and it's another form of a reactive protocol. The black-hole attack is a major attack that drastically decreases the packet delivery ratio during a data transaction in a routing environment. In this attack, the attacker's node acts as the shortest path to the target node itself. If the attacker node receives the data packet from the source node, all obtained data packets are excluded from a routing network. A trust-based routing scheme is suggested to ensure secure routing. This routing scheme is divided into two stages, i.e., the Data retrieval (DR), to identify and preserve each node data transfer mechanism in a routing environment and route development stage, to predict a safe path to transmit a data packet to the target node.

The proposed model in this paper is the intrusion detection techniques for mobile ad-hoc networks, which use collaborative efforts of nodes in a neighborhood to detect a malicious node in that neighborhood. The technique is designed for detection of malicious nodes in a neighborhood of nodes in which each pair of nodes in the neighborhood are within radio range of each other. Such a neighborhood of nodes is known as a clique. The technique uses message passing between the nodes. A node called the monitor node initiates the detection process. Based on the messages that it receives during the detection process, each node determines the nodes it suspects to be malicious and send votes to the monitor node. The monitor node upon inspecting the votes determines the malicious nodes from among the suspected nodes. The proposed intrusion detection system is independent of any routing protocol.

The Internet of Things (IoT) is now growing dramatically on various levels and helps to digitize various vital industries quickly. The most difficult obstacle for BCIs to overcome is the fact that not everyone has the same brain. Every new session requires the BCI to learn from the user's brain, which is accomplished via the use of Machine Learning. However, this learning process is time-consuming. Calibration time refers to the amount of time it takes for the BCI to adapt to the user's brain in order to properly categorise their thoughts and determine their meaning. The patient has had to wait an arduous and tiresome length of time for the system to be completely functioning up until now because of this calibration, which may take up to 20 - 30 minutes. The aim of this thesis was to find a way to decrease the amount of time required for calibration to the smallest amount feasible. In the first section of this paper, a first effort is made to determine the optimum number of features required for the BCI to operate reasonably, taking into consideration all of the calibration data provided. When the results were averaged across five participants, the percentage of properly identified thoughts was just 67.15 percent. Transfer learning was used in order to improve the performance of the BCI while simultaneously decreasing the calibration time. It is feasible to decrease the amount of calibration required for the categorization of thoughts coming from a new target subject by using knowledge collected from previously recorded subjects to the greatest extent possible in Transfer Learning. It was determined that existing methods were superior, and a new methodology was created that required just 24 seconds of calibration data while accurately identifying 86.8% of the thoughts. In order to alleviate mental stress and anger, the system suggested fits effectively with a deep learning network. This paper proposes a brain learning framework that uses a neural network model that is complex in nature and uses IoT for data collection from various wearable devices and the same can be used for modelling the brain functions.