The rapid proliferation of Internet of Things (IoT) devices has significantly increased the attack surface for large-scale botnet operations. While previous research, including detailed analyses using Cowrie and IoTPOT frameworks, has studied IoT botnet behavior, these studies often rely on retrospective datasets, isolated protocol analyses, or hard-to-replicate setups. This paper addresses that gap with two main contributions: a structured review of ten influential IoT security studies from the USENIX Security Symposium and a confirmatory empirical experiment deploying Cowrie and IoTPOT honeypots simultaneously on a Microsoft Azure cloud-based virtual machine. Unlike earlier studies that focus on single protocols or large-scale environments, this work acts as a validation study, confirming well-known IoT botnet behaviors, including credential brute-force attacks, Mirai-style commands, and Telnet dominance, using real-time attack data collected from a reproducible, affordable cloud environment that simulates known IoT vulnerabilities (such as CVE-2016-10401, CVE-2017-17215, and CVE-2014-9222). Rather than revealing new attack methods, this study explicitly verifies the persistence of behaviors first documented almost ten years ago. The data indicates that attackers continue to exploit basic authentication flaws and reuse long-standing command sequences, confirming that core IoT vulnerabilities remain prevalent despite a decade of security research. It also highlights the ongoing gap between research progress and industry implementation. The analysis situates these findings within the broader evolution of IoT botnets, from early centralized command-and-control structures like Mirai to more resilient peer-to-peer networks that use anonymized channels and target high-wattage devices for power-grid manipulation. This study shows that small, cloud-based honeypots are valuable for continuous threat monitoring, model validation, and security assessments, providing a practical, reproducible approach for ongoing IoT security research.

Customer Relationship Management (CRM) systems are essential tools for understanding customer behavior, enhancing engagement, and facilitating business growth. As more customer data is collected, the risks of privacy breaches and unauthorized access increase, making the challenge of data protection more significant. The primary focus of this research is to construct and deploy a hybrid Bobcat-based Federated AES Model (BbF-AESM) to enhance CRM practices via the confidentiality and processing of sensitive customer information. In this approach, Bobcat optimization is used to adjust the model’s parameters for better results and Accuracy. Federated Learning (FL) enables collaborative training of the model without exposing raw customer data, and AES encryption ensures that the data remains private during both transmission and storage. The proposed model was tested and validated against CRM databases in a Python environment, and performance evaluation utilized measures such as F-measure, Recall, Accuracy, AUC, and Precision. The outcome showed that the hybrid BbF-AESM surpassed other systems, achieving 98.5% accuracy, while the error rate was just 1.5%. These results emphasize the model’s ability to provide exact customer predictions and secure data management. Overall, the proposed framework facilitates improved privacy preservation and enhances computational efficiency and scalability in CRM systems.

The goal of this research is to develop an advanced intelligent model capable of identifying spam calls and fake news, while also enhancing the reliability and accuracy of spam detection. Available models face numerous challenges, including low accuracy, high error rates, slow processing speeds, and difficulties in handling noisy, unbalanced, and complex datasets. To overcome these disadvantages, the current work presents a new model, known as the Arctic Puffin-based Convolutional Detection Model (APbCDM). This model incorporates suitable preprocessing methods with the Arctic Puffin Optimization (APO) algorithm to extract meaningful features and suppress noise in the dataset. It then applies the filtered features through a convolutional network for appropriate classification. The results of the experiment indicate that the model proposed in this paper achieves an accuracy level of 99 percent. It also has precision, recall, and F1-score levels of 99 percent, along with a low error rate of just 1 percent, clearly indicating its superiority over traditional methods. The current work presents a robust, precise, and intelligent approach to detecting spam calls and fake news. Index Terms—Fake News, Convolutional Neural Network, Data Preprocessing, Feature Selection, Spam Call Detection.

To address the challenges of data security governance under new conditions and align with technological trends in data security, this paper proposes a graph algorithm-based method for identifying key personnel with critical permissions in the practical applications of large state-owned enterprises. This method can uncover potential permission influence factors within the system and evaluate the weight of influence from different perspectives, providing highly interpretable identification results. To tackle the issue of detecting anomalous user and entity behaviors in data security governance, a user and entity behavior anomaly detection method based on Generative Adversarial Networks (GAN) is introduced. Experimental results show that the proposed method achieves higher precision, recall, and F1-score averages compared to baseline models; specifically, an average F1-score of 0.75 versus 0.72 for LSTM-based TadGAN, 0.62 for ARIMA, and 0.65 for a commercial UEBA baseline across the three evaluation datasets. A data security platform was designed and developed, which plays a significant role in reducing data security risks, assisting enterprise compliance, and promoting data development and utilization. This platform has been applied in various centralized data management projects and meets the big data processing requirements in secure environments, demonstrating strong application and promotional value.

Due to the increasing complexity of cyberattacks, old-school cybercrime detection methods are no longer effective. This chapter looks at how machine learning-based intrusion detection systems and anomaly detection solutions can revolutionise the way cybersecurity is done today. By using various different machine learning (ML) algorithms, such as supervised, unsupervised, and reinforcement learning and find outliers (e.g. identify anomalies), detect new types of threats, and automatically respond to security incidents. This chapter provides a thorough overview of how ML is used for intrusion detection, including the use of deep learning algorithms for threat intelligence, behavioural and static analysis of malware, identifying phishing schemes using natural language processing, and detecting zero-day attacks. Additionally, this chapter dealing with unbalanced datasets, defending against adversarial attacks, using federated learning to cover multiple locations, and enabling explainability for ML-based cybersecurity.