Intrusion Detection and Prevention Systems (IDPS) play a key role in protecting networks by keeping an eye out for suspicious activity, spotting threats, and taking action to stop them. These systems were originally designed for traditional, fixed networks, but they struggle to keep up with the fast-paced and constantly changing nature of cloud computing environments. Cloud computing has revolutionized technology, bringing many innovations in how organizations operate. Organizations rely heavily on the use of cloud storage to store and retrieve their sensitive data. Security issues in the cloud computing environment are a big challenge as, despite various protection measures, the cloud environment is vulnerable to security threats. Intrusion Detection and Prevention System (IDPS) is a significant component in securing the cloud environment against emerging threats in cyber-attacks. This paper takes a close look at intrusion detection systems (IDS) that are specifically built for cloud computing. The cloud brings its own set of challenges like constantly changing resources, sharing space between many users, and limited visibility into all the network traffic. Unlike traditional IDS that work in fixed, local networks, cloud-based IDS have to handle traffic that moves between virtual machines and scale up or down quickly. Cloud computing has transformed over time, improving access to scalability while offering vulnerabilities that increase the probability of intrusion or attacks. This review addresses these research gaps by comprehensively surveying state-of-the-art IDPS techniques tailored for cloud computing environments. IDPS is further classified into different categories, such as signature-based, anomaly-based, and hybrid-based. Recently, combining Machine Learning (ML) and Deep Learning (DL) with Intrusion Detection Systems (IDS) has shown to be very effective, as it allows for more precise detection and large-scale use. However, notable challenges include small dataset sizes, imbalanced datasets, and high expenses. These challenges mainly focus on creating adaptive systems that identify intrusions in real time. To tackle this, attention is directed towards ensemble learning and edge computing. The outcomes of these initiatives are being used to create a strong and efficient IDS that fits well with the changing nature of cloud environments. This survey provides a comprehensive analysis of current IDPS methodologies and future perspectives, aiming to contribute to developing robust and efficient cloud security solutions.

The integration of Generative Adversarial Networks (GANs) with Genetic Algorithms (GAs) represents a novel approach to enhancing cryptographic methods, particularly in addressing challenges posed by quantum computing and increasingly sophisticated cyber threats. This research focuses on improving encryption strength, adaptability, and robustness against decryption attempts. By leveraging the optimization capabilities of GAs to evolve neural network architectures within a GAN framework, we significantly enhance the generator's ability to produce secure, quantum-resistant encryptions. The genetic algorithm optimized both the generator and discriminator networks over 300 generations, reducing generator loss from an initial 0.78 to a stable 0.65, while increasing discriminator loss, indicating improved encryption complexity. This study demonstrates the feasibility of using evolutionary techniques and adversarial training to create a dynamic, self-evolving cryptographic system, providing a foundation for future cryptographic innovations in quantum-resistant security. The methodology combines GA-driven network optimization and GAN-based adversarial training to address the challenges of quantum decryption and advanced adversarial attacks, setting new benchmarks for cryptographic security.

Summary In the rapidly evolving domain of Mobile Ad‐hoc Networks (MANETs), where their deployment spans critical military operations to essential organizational communication infrastructures, the pervasive threat of security breaches casts a long shadow on the networks' operational integrity and reliability. Central among these threats are sleep deprivation attacks, a particularly insidious form of cyber aggression that exploits the inherent decentralized and self‐organizing characteristics of MANETs to exhaust the energy reserves of nodes, compromising the network's stability and performance. This paper embarks on a journey to confront this challenge head‐on, introducing a pioneering and holistic defense mechanism that integrates a cumulative priority‐based model for the selection of cluster heads, ingeniously augmented by the principles of Chebyshev's Inequality for optimal load balancing. This novel strategy is designed not only to counteract the direct impacts of sleep deprivation attacks but also to address the underlying vulnerabilities of MANETs that these attacks exploit. Through a rigorous series of simulations, conducted across a spectrum of network scenarios to test the resilience and adaptability of our proposed model, we have observed a commendable success rate of 98% in neutralizing sleep deprivation attacks. By leveraging the dynamic nature of MANETs and integrating advanced statistical methods for load distribution and cluster management, our model offers a robust framework that significantly improves network performance and energy efficiency. This, in turn, fosters a more sustainable and reliable network environment, crucial for the high‐stakes applications MANETs support. By championing a comprehensive and adaptable approach to security, this study promises to reinstate user trust and ensure the continued reliability of these indispensable networks, securing their place as a cornerstone of modern communication infrastructure in the face of evolving cyber threats.

Summary In this research, we present an innovative cryptographic key generation method utilizing a Generative Adversarial Network (GAN), enhanced by Merkel tree verification, marking a significant advancement in cryptographic security. Our approach successfully generates a large 6272‐bit key, rigorously tested for randomness and reliability using the Dieharder and NIST test suites. This groundbreaking method harmoniously blends cutting‐edge machine learning techniques with traditional cryptographic verification, setting a new standard in data encryption and security. Our findings not only demonstrate the efficacy of GANs in producing highly secure cryptographic keys but also highlight the effectiveness of Merkel tree verification in ensuring the integrity of these keys. The integration of merkel tree in our method provides a means to efficiently verify the authenticity of the large generated key sets. This research has broad implications for the future of secure communications, providing a robust solution in a world increasingly reliant on digital security. The integration of machine learning and cryptographic principles opens up new avenues for research and development, promising to bolster security measures in an era where digital threats are constantly evolving. This work contributes significantly to the field of cryptography, offering a novel perspective and robust solutions to the challenges of digital data protection.

Blockchain has attracted tremendous attention in recent years due to its significant features including anonymity, security, immutability, and audibility. Blockchain technology has been used in several nonmonetary applications, including Internet-of-Things. Though blockchain has limited resources, and scalability is computationally expensive, resulting in delays and large bandwidth overhead that are unsuitable for many IoT devices. In this paper, we work on a lightweight blockchain approach that is suited for IoT needs and provides end-to-end security. Decentralization is achieved in our lightweight blockchain implementation by building a network with a lot of high-resource devices collaborate to maintain the blockchain. The nodes in the network is arranged in sorted order w.r.t execution time and count to reduce the mining overheads and is accountable for handling the public blockchain. We propose a distributed execution time-based consensus algorithm that decreases the delay and overhead of the mining process. We also propose a randomized node-selection algorithm for the selection of nodes to verify the mined blocks to eliminate the double-spend and 51% attack. The results are encouraging and significantly reduce the mining overhead and keep a check on the double-spending problem and 51% attack.