Distributed Denial of Service (DDoS) attacks are among the primary concerns in internet SECURITY today. Machine learning can be exploited to detect such attacks. In this paper, a multi-layer perceptron model is proposed and implemented using deep machine learning to distinguish between malicious and normal traffic based on their behavioral patterns. The proposed model is trained and tested using the CICDDoS2019 dataset. To remove irrelevant and redundant data from the dataset and increase learning accuracy, feature selection is used to select and extract the most effective features that allow us to detect these attacks. Moreover, we use the grid search algorithm to acquire optimum values of the model’s hyperparameters among the parameters’ space. In addition, the sensitivity of accuracy of the model to variations of an input parameter is analyzed. Finally, the effectiveness of the presented model is validated in comparison with some state-of-the-art works.

Purpose: Food SECURITY is a critical global challenge that is influenced by research and innovation in the field. Therefore, the objective of this study is to analyze the scientific output of developing countries in food SECURITY and examine its relationship with patents and Gross Domestic Product (GDP).Methodology: This applied research utilized the Scientometric approach. A total of 8,416 papers published between 1992-2023 in the field of food SECURITY by developing countries were included in the study using citation databases from Clarivate Analytics. Additionally, patent registrations from the WIPO database and GDP data from the World Bank were analyzed. Information was collected through note-taking, and the data was analyzed using Pearson's correlation coefficient.Findings: The findings reveal an upward trend in the publication and citation of scientific outputs related to food SECURITY in developing countries. China has higher numbers of papers, patents, GDP, and food production index compared to Iran, Japan, and South Korea. There is also a positive correlation observed between population and the number of papers, gross production and the number of papers, food production and the number of published papers, as well as the number of patents and papers citing scientific outputs of countries.Conclusion: These results highlight the significant relationship between increasing scientific output, GDP, the number of patents, and food SECURITY. Greater emphasis on food SECURITY contributes to enhanced scientific output, GDP, and innovation. Similarly, increasing scientific output, GDP, and innovation positively impact food SECURITY in countries.Value: This study emphasizes the importance of scientific outputs in driving technological advancements, innovations, and ultimately, ensuring food SECURITY in developing countries.

Background and aim: Virtual social NETWORKs, especially the telegram messenger NETWORK, have essential functions in the transition society and have been directly linked to SECURITY and ethical issues in societies. The purpose of this study is to determine the effect of telegram messenger NETWORK on ethical SECURITY in Tehran. Research methodology: This study is a survey research using a researcher-made questionnaire tool to collect data. The statistical population of the study consistes of all users of telegram messenger NETWORK in Tehran. Data analysis was done using SPSS software and statistical tests. Findings: Findings indicate that the provision or threat of moral SECURITY is the result of the components of social behavior changes such as privacy violations (abuse of private information) and the spreading of false rumors and produced content (textual, audio, visual) about individuals and social and ethical issues. Targeted use of the telegram and ease of access to this messenger NETWORK are other influential variables. Conclusion: The results of this study shows that policy making and strategic planning (proactive and opportunistic measures) for targeted use and content guidance as well as legal and formal oversight and control levers, including filtering of some of the offending channels by responsible organizations (counter and counter measures), seems essential in order to maintain and preserve moral SECURITY.

This paper presents a novel method to combine neural NETWORK and Ward equivalent external NETWORK modeling to achieve advantages of both methods for on-line voltage SECURITY assessment. The demonstrated method includes simplicity of Ward equivalent model and due to application of neural NETWORK techniques it is very fast and accurate. In this method ANN is used to obtain boundary buses power injections. The developed method in applied to IEEE 30 bus test system and results highlighted the anticipated speed and accuracy.

The proposed models to assess the SECURITY risks of bridges are generally designed based on the product of three-factor: probability (O), vulnerability (V), and importance (I). In this paper, the importance of bridge (I) and its changes due to the uncertainty of NETWORK topology during future NETWORK development programs were discussed. To measure and compare the relative importance of bridges, two groups of unique importance and the NETWORK-based importance of bridges were considered. Given that the NETWORK-based characteristics of bridges change during NETWORK development, a numerical example was presented to compare different decision-making approaches in selecting bridges (with and without considering the changes in the importance of bridge NETWORKs due to NETWORK changes). In this example, the Ahwaz inter-city transportation NETWORK was examined. The results showed that some bridges, such as B3, which were not important in the initial, became important during the development process. In contrast, in some bridges, such as B5, the relative importance was high at first, but during the development process, their relative importance decreased. It was also observed that a number of bridges such as B1, B6, and B7 are always important. In contrast, bridges such as B4 are always considered insignificant and NETWORK changes do not place them among the important bridges in any period.

IoT devices has witnessed a substantial increase due to the growing demand for smart devices. Intrusion Detection Systems (IDS) are critical components for safeguarding IoT NETWORKs against cyber threats. This study presents an advanced approach to IoT NETWORK intrusion detection, leveraging deep learning techniques and pristine data. We utilize the publicly available CICIDS2017 dataset, which enables comprehensive training and testing of intrusion detection models across various attack scenarios, such as Distributed Denial of Service (DDoS) attacks, port scans, botnet activity, and more. Our goal is to provide a more effective method than the previous methods. Our proposed deep learning model incorporates dense transition layers and LSTM architecture, designed to capture both spatial and temporal dependencies within the data. We employed rigorous evaluation metrics, including sparse categorical cross-entropy loss and accuracy, to assess model performance. The results of our approach show outstanding accuracy, reaching a peak of 0.997 on the test data. Our model demonstrates stability in loss and accuracy metrics, ensuring reliable intrusion detection capabilities. Comparative analysis with other machine learning models confirms the effectiveness of our approach. Moreover, our study assesses the model's resilience to Gaussian noise, revealing its capacity to maintain accuracy in challenging conditions. We provide detailed performance metrics for various attack types, offering insights into the model's effectiveness across diverse threat scenarios.