Healthcare is considered significant topic in the recent research area. However, one of the most commonly diseases which is heart diseases disease. The possibility of early detection to reduce the number of deaths because it is difficult to predict a heart disorder quickly. Recently, many researchers focused on the implementation of several feature extraction techniques and the help of artificial intelligence algorithms to classify this disease, but classification accuracy remained the only difference between these studies. In this paper, the proposed work for the classification of heart diseases was implemented and tested after selecting methods and techniques for data pre-processing and extracting important features that led to obtaining a competitive classification accuracy that reached higher than 93.5% compared to related studies. This finding encourages us and other field researchers to use methods for feature extraction and other strategies described in this paper to classify other diseases.

Cyber-attacks involve stifling processes and activities, conciliating data, or restricting data access by carefully modifying computer systems and networks with malware. There has been a significant increase in these types of attacks over time. Due to the rise in complexity and structure, advanced defensive methods are needed. In the face of growing security threats, traditional methods of identifying cyber-attacks are ineffective. In this paper, the intelligent of intrusion a detection system is suggested. Moreover, the suggested system attempts to evaluate the capability of the k-nearest neighbour's algorithm (KNN) in terms of distinguishing between authentic and tampered data. A reliable dataset named the Multi-Step Cyber-Attack Dataset (MSCAD) is utilized to determine the behavior Among the new sorts of attacks. Moreover, 60% of the dataset was utilized for training the model, and a remaining 40% was used for testing. Evaluation metrics like accuracy, precision, recall, and F1 score are used. Experiments suggest that the proposed system-based KNN could enhance detection performance. Moreover, the suggested approach increases detection accuracy while minimizing false alarms.

With a surge in the usage of systems that largely depend on networking and programming, the need for cybersecurity has grown as well. Cyberattacks are a rising threat to companies and people. The Distributed Denial of Service (DDoS) attack is one of the destructive hacks that have swiftly acquired appeal among hackers. In this work, a security system is proposed to prevent DDoS. In other words, it has the ability to protect external and internal communication systems from attacks. The primary contribution of this work is to acquire the best accuracy based on time series. Multiple machine learning algorithms are applied and compared between them. The Random Forest accuracy is 100% and the XGBoost was 91% using the same data set.

SCADA (Supervisory Control and Data Acquisition) is a crucial ICS used in gas pipelines, power grids, and healthcare, this study discusses the importance of intrusion detection systems (IDS) systems, highlighting the DNP3 protocol for communication, IDS intrusion detection systems, and assaults. It compares and debates past research on the topic, emphasizing the need to detect irregularities and maintain safety in SCADA systems, as security breaches pose significant risks.

In the ever-evolving environment of digital security, the value of cryptographic systems in preserving data and communications cannot be emphasized. However, the introduction of side-channel attacks has presented a substantial hazard, leveraging minor information breaches from the physical implementations of cryptographic algorithms. This research, via a thorough examination of literature spanning several years, tries to consolidate and classify the diverse approaches employed in side-channel assaults. This research dives into the fundamental weaknesses that these assaults exploit, spanning elements such as power usage, electromagnetic radiation, timing problems, and auditory emissions. To demonstrate the real-world ramifications of side-channel vulnerabilities, the paper presents realistic examples and case studies, providing light on the possible repercussions of these assaults. By classifying side-channel assaults depending on their strategy and identifying important instances within each category, this research elucidates the broad landscape of side-channel threats. It also investigates the severe effect of these attacks on cryptographic systems and its implications for general security, highlighting the critical need for comprehensive countermeasures. This thorough research gives a full evaluation of side-channel assaults, concentrating on their methodology, effect, and the increasing realm of response tactics. Understanding the subtleties of side-channel attacks is crucial to strengthening the security of cryptographic systems. As such, this study offers as a helpful resource for academics, practitioners, and policymakers contending with the evolving environment of side-channel assaults. It emphasizes the continual necessity for study and joint attempts to reinforce cryptography solutions in a more linked culture.

Communication, social interaction, behavior, and sensory processing are all negatively impacted by the neurodevelopmental disease known as autism spectrum disorder (ASD). The word "spectrum" is included in the name because there is such a broad variety of symptoms and degrees of impairment. The health and well-being of children with autism spectrum disorder (ASD) can be greatly improved by early diagnosis and intervention. The current detection techniques are based on the opinion of specialists, which is subjective and expensive. In this research, we suggest a machine learning strategy for ASD diagnosis that incorporates a suite of machine learning techniques. Using it has the potential to save money and increase detection efficiency. To begin, we performed pre-processing to extract characteristics from the data. Then, classify the data with a 0.997% accuracy using four machine learning (ML)-based methods: The Random Forest, logistic regression, support vector machine (SVM) and K-nearest neighbors algorithm (KNN). The findings of this research provide promising evidence for the efficacy of the machine learning classification technique used to diagnose ASD at an early age.

The Internet of things (IoT) allows billions of computer and networking devices to be interconnected. Digital entities such as sensors, Radio-frequency identification (RFID), Internet and localization technologies enable everyday objects to be transformed into intelligent objects, which can communicate with one another. The built-in sensors in intelligent objects track and collect various types of data about equipment, the environment and human social life. Although the IoT is useful, safety susceptibility is a major concern. There are universal and continuous interconnections between people, devices, sensors and services. Even if the security system is well built, smartly configured, implemented effectively and managed correctly, it must be human-made and are not resistant to security threats. Therefore, the conception of cyber security solutions requires a human element. To fight attacks, this paper presents an Intrusion Detection System (IDS) based on Smart Techniques such as k-nearest neighbors (KNN) and Random Forest (RF) algorithms which take data as input for spotting harmful activities. The methodology of IDS was created for identifying malicious activities of network traffic utilizing a set of features. Designing efficient IDS involves a data source that incorporates a collection of attributes for evaluating its performance while identifying normal and attack instances. This is one of the challenges that we strive to address in this study. Based on KNN and RF algorithms has presented a collection of features for spotting harmful activities that take advantage of IoT applications to utilize these procedures. The data sources are taken from the UNSW-NB15 source files.

Credit card is one of the modern payment methods widely spread all over the world. It provides excellent facilities in purchasing as well as selling operations. However, it suffers from fraud problems, causing considerable economic losses to banks, institutions, and individuals, amounting to billions of dollars annually. That has made great interest in finding systems and means with outstanding capabilities to confront fraud, whose patterns in addition to methods are increasing dramatically. One of the most prominent techniques used by researchers in this field is Machine Learning (ML) techniques. In this paper, we proposed some of the classification ML algorithms such as Logistic regression(LR), Linear Discriminant Analysis (LDA), and Naïve Bayes(NB), additionally, the boosting algorithm XGBoost to create models capable of detecting fraud. The dataset from Kaggle. We used performance metrics such as accuracy, precision, f1, recall, AUC confusion matrix to evaluate the models' performance. The XGBoost model presented the best results compared to other models.

Deepfake is heavily based on artificial intelligence and machine learning to generate audio content and visuals with an extremely high potential to deceive. In this paper, a new detection system to identify any deepfake for audio or images. In other words, transfer learning techniques are used to present an intelligent detection system of deepfake videos. In this work, a support vector machine is employed for the detection process. Outstanding results are obtained from the train and test this system with various types of images that are real or fake.

Mobile Ad hoc Networks (MANET) provide a service in one way or another through network applications in several diverse areas due to the multiple characteristics of MANET, such as high-level mobility, decentralization of nodes, and physical insecurity. The Intrusion Detection System (IDS) function detects threats and stops them before they disrupt the network. Supervised machine learning techniques are easy to implement and comprehend because they use the knowledge and experience gathered from the available data to classify network nodes into normal or malicious. To enhance security in MANET networks in this paper, we proposed a security detection system employing classify misbehavior of nodes depending on supervised machine learning techniques such as Random Forest (RF) and Naive Bayes(NB) techniques. Using a network simulator-2 (ns-2) simulation was made to produce a data set, explained Our experimental results for our proposed system have good accuracy for detecting intrusion in the system. The RF was more efficient.

Recently, millions of medical information passed different media to reach their destination without any error. The introduction of advanced media including communications, wireless networks, mobile networks and Internet offer wide range of e-health application. Electrocardiogram (ECG) waveform is an important issue in e-health in which it recognizes the heart activities and it gives an efficient indication about the patient. The most important issue of ECG waveform is to transmit and receive this waveform with an efficient way. This means ECG waveform must reach its destination secure and accurate. The implemented approach introduces an efficient way for compression and encryption of ECG waveform. This approach based on both discrete wavelet transforms (DWT) and shifted fast Fourier transform (FFT). The obtained results indicated that there is 100% of similarity between transmitted and received signal in addition there is a compression ratio of ¼ when applying second level DWT.

Vehicular ad hoc networking (VANET) have become a significant technology in the current years because of the emerging generation of self-driving cars such as Google driverless cars. VANET have more vulnerabilities compared to other networks such as wired networks, because these networks are an autonomous collection of mobile vehicles and there is no fixed security infrastructure, no high dynamic topology and the open wireless medium makes them more vulnerable to attacks. It is important to design new approaches and mechanisms to rise the security these networks and protect them from attacks. In this paper, we design an intrusion detection mechanism for the VANETs using Artificial Neural Networks (ANNs) to detect Denial of Service (DoS) attacks. The main role of IDS is to detect the attack using a data generated from the network behavior such as a trace file. The IDSs use the features extracted from the trace file as auditable data. In this paper, we propose anomaly and misuse detection to detect the malicious attack.

Expansion in the use of the World Wide Web led to the creation of a new phenomenon in our daily life which is a phenomenon of electronic commerce. E-commerce is generally known as any form of trade or administration or exchanging of information that are conducted by using information and communication technologies. Capacity of electronic commerce is expected to grow rapidly, and play a vital role as a major means of doing business in the digital world. This study aims to sophisticate and increase the distribution of E-commerce by eliminating one of the main obstacles that stand against the deployment and development of electronic commerce, such as, reliability. Thus the customer or company will assure of a selling or purchase depending on the new protocol which is called B2B2C. This protocol will support the kinds of electronic commerce by a new one which will be a third party mediator. The inclusion of this mediator will increase the safety and reliability of business exchanging through depending on more reliable policies and eliminate the problem of low usage Arabic. Therefore, e-commerce will be increased despite that some developing countries now are virtually non-existent according to the current statistics.