The exponential growth of Internet of Things (IoT) devices integrated with fifth-generation (5G) wireless networks has created unprecedented opportunities for ultra-low-latency applications while introducing complex security vulnerabilities and computational challenges. This paper presents a comprehensive framework for deploying adaptive lightweight Convolutional Neural Networks (CNNs) in 5G-enabled IoT environments to address intrusion detection, intelligent traffic classification, and dynamic resource optimization. We propose a novel multi-objective optimization approach that integrates Adaptive Depthwise Separable Convolutions (ADSC), Dynamic Quantization-Aware Training (DQAT), and Real time Pruning Strategy (RPS) specifically designed for 5G network slicing architectures. Our methodology incorporates federated learning principles, edge-cloud collaboration, and context-aware adaptation mechanisms. Comprehensive evaluation on multiple datasets, including NF-ToN-IoT-v2, NSL-KDD, and CICIDS-2017, demonstrates superior performance with 97.8% accuracy in multi-class attack detection, 76% reduction in computational overhead, 71% decrease in energy consumption, and 42% improvement in network throughput. The framework achieves inference times under 8.5ms on edge devices while maintaining robust security postures across heterogeneous IoT deployments. Statistical significance testing and large-scale ablation studies verify the effectiveness of each of the suggested elements.

Current network security technologies face new threats from determined attackers employing advanced evasion techniques such as IP spoofing, tiny fragment attacks, tunneling, and HTML smuggling. Conventional intrusion detection and prevention systems (IDS/IPS) have significant limitations in detecting zero-day attacks and sophisticated threats that can continuously alter their attack vectors. This paper presents a novel deep learning-driven, multilayer intrusion detection and prevention framework that integrates network-based IDS/IPS, host-based intrusion detection systems (HIDS), and honeypot technologies with advanced machine learning models, including graph neural networks (GNNs), autoencoders, and transformers. The framework employs adaptive learning mechanisms to enhance resilience against evasion techniques while maintaining low false positive rates. Experimental evaluation using diverse attack datasets demonstrates superior performance, achieving 97.3% detection accuracy for zero-day attacks and 94.8% resilience against advanced evasion techniques, significantly outperforming existing state-of-the-art solutions. The proposed framework contributes to cybersecurity research by introducing innovative multilayer correlation mechanisms, adaptive threat modeling, and evasion-resilient detection algorithms.

Man-in-the-Browser (MitB) attacks represent a sophisticated class of web-based threats that manipulate browser functionality to intercept and modify user transactions in real-time. Traditional server-side detection mechanisms often fail to identify these attacks due to their client-side nature and encrypted communication channels. This paper presents a novel client-side runtime integrity agent that employs forensic monitoring and machine learning-based anomaly detection to identify MitB attacks at their source. The proposed system integrates DOM integrity verification, memory forensic analysis, and behavioral pattern recognition to detect malicious browser modifications before they can compromise user sessions. Our experimental evaluation demonstrates a detection accuracy of 97.3% with a false positive rate of 2.1%, significantly outperforming existing client-side detection methods. The system successfully identified various MitB attack vectors, including Zeus, SpyEye, and custom injection payloads, while maintaining a minimal computational overhead of less than 3% CPU utilization.

Ad hoc networks, known as infrastructure-less networks, are composed of mobile nodes that connect without a centralized system controlling them. These networks have a wide range of potential applications, including emergency response, events, military operations, wireless access, and intelligent transportation. They can take on various forms, such as wireless sensor networks, wireless mesh networks, and mobile ad hoc networks. Because users in these networks can move around at any time, routing protocols must adapt to the constantly changing network layout. However, these networks are also susceptible to various security threats, including DDoS attacks. This paper aims to analyze the performance and impact of security attacks on the performance of reactive and proactive routing protocols in CBR connection patterns with different pause times. The analysis is provided in metrics such as throughput, packet loss, end-to-end delay, and load. The simulation results show that, on average, the OPNET Modeler simulator analyzed the performance results under DDoS attacks under voice and video traffic conditions. Furthermore, the paper explores the use of Honeypot intelligent agents as a solution to increase security by creating a dummy node to fool DDoS attackers. The results show that the OLSR protocol is most affected by DDoS attacks in terms of quality-of-service metrics such as packet loss, throughput, end-to-end delay, and load. The number of responses to the honeypot solutions differs for each protocol.