The exponential growth of the Internet of Things (IoT) has significantly broadened the attack surface for cyber threats, necessitating robust and adaptive security frameworks. This study introduces a novel suite of hybrid deep learning-based Intrusion Detection System (IDS) models tailored for large-scale IoT environments. Specifically, we propose and optimize three IDS models-CNN-LSTM, GRU-AE, and Bi-LSTM-CNN-leveraging hybrid architectures to address the challenges of real-time threat detection, computational limitations, and adaptive learning. The models are evaluated on two benchmark datasets, BoT-IoT and CICIDS2017, achieving average accuracies of 97.8%, 98.3%, and 98.6%, and F1-scores of 97.5%, 98.1%, and 98.4%, respectively. These results demonstrate a performance improvement of 6%-12% in accuracy and 8%-15% in F1-score over conventional IDS methods, with false positive rates consistently below 2.5% and detection rates exceeding 98.7%. The proposed models are optimized for lightweight deployment and low-latency detection, reducing inference time by up to 35% and energy consumption by 22% compared to baseline deep learning models-ensuring feasibility in resource-constrained environments. Furthermore, the study explores mechanisms for continuous learning, enabling a 15%-20% improvement in adaptability to previously unseen attack patterns. Interpretability is enhanced through the integration of SHAP (SHapley Additive exPlanations) values, with over 92% of critical prediction decisions explained by the top 10 contributing features. A comparative analysis highlights not only performance gains but also the models' robustness, scalability, and resilience under adversarial conditions. The results confirm that the proposed hybrid IDS models offer a scalable, efficient, and interpretable solution for enhancing IoT network security. This work contributes a comprehensive and deployable framework to address the evolving landscape of cyber threats in the IoT ecosystem.

The rapid expansion of the Internet of Things (IoT) has significantly improved the various aspects of our daily life. However, along with its benefits, new security threats such as Denial of Service (DoS) attacks and Botnets have emerged. To adopt this technology and integrity of IoT environment, detection of such attacks become crucial. This paper proposes a hybrid deep learning model that combines Convolutional Neural Network (CNN) and Gated Recurrent Units (GRUs) to classify the IoT security threats. The CNN is used to extract the spatial features from the network data, where on the other hand GRUs used for capturing the temporal dependencies. This combination makes the model effective at analysing both static and dynamic aspects of network data. Further, to optimize the performance of the proposed hybrid model, self-upgraded Cat and Mouse Optimization (SUCMO) algorithm is employed, a state of art optimization technique. The SUCMO algorithm fine-tunes the deep learning model's hyperparameters to improve classification accuracy. The proposed model is evaluated through experiments on two different datasets i.e., UNSW-NB15 and BoT-IoT, and results demonstrates that proposed work outperforms the traditional work as well as state of the art works.

The Internet of Things (IoT) is being prominently used in smart cities and a wide range of applications in society. The benefits of IoT are evident, but cyber terrorism and security concerns inhibit many organizations and users from deploying it. Cyber-physical systems that are IoT-enabled might be difficult to secure since security solutions designed for general information/operational technology systems may not work as well in an environment. Thus, deep learning (DL) can assist as a powerful tool for building IoT-enabled cyber-physical systems with automatic anomaly detection. In this paper, two distinct DL models have been employed i.e., Deep Belief Network (DBN) and Convolutional Neural Network (CNN), considered hybrid classifiers, to create a framework for detecting attacks in IoT-enabled cyber-physical systems. However, DL models need to be trained in such a way that will increase their classification accuracy. Therefore, this paper also aims to present a new hybrid optimization algorithm called “Seagull Adapted Elephant Herding Optimization” (SAEHO) to tune the weights of the hybrid classifier. The “Hybrid Classifier + SAEHO” framework takes the feature extracted dataset as an input and classifies the network as either attack or benign. Using sensitivity, precision, accuracy, and specificity, two datasets were compared. In every performance metric, the proposed framework outperforms conventional methods.

Because of the rise in the number of cyberattacks, the devices that make up the Internet of Things (IoT) environment are experiencing increased levels of security risks. In recent years, a significant number of centralized systems have been developed to identify intrusions into the IoT environment. However, due to diverse requirements of IoT devices such as dispersion, scalability, resource restrictions, and decreased latency, these strategies were unable to achieve notable outcomes. The present paper introduces two novel metaheuristic optimization algorithms for optimizing the weights of deep learning (DL) models, use of DL may help in the detection and prevention of cyberattacks of this nature. Furthermore, two hybrid DL classifiers, i.e., convolutional neural network (CNN) + deep belief network (DBN) and bidirectional long short-term memory (Bi-LSTM) + gated recurrent network (GRU), were designed and tuned using the already proposed optimization algorithms, which results in ads to improved model accuracy. The results are evaluated against the recent approaches in the relevant field along with the hybrid DL classifier. Model performance metrics such as accuracy, rand index, f-measure, and MCC are used to draw conclusions about the model’s validity by employing two distinct datasets. Regarding all performance metrics, the proposed approach outperforms both conventional and cutting-edge methods.

The term “Internet of Things” (IoT) is used to describe the global network of billions of devices, buildings, cars, and other physical things that are interconnected and exchange information. IoT security is necessary for the secure connection of devices and the components of such devices, as well as for the protection of those devices from cyberattacks which includes DoS, Botnet, brute force and SQL injection. In order to mitigate these potential attacks, several security methods and algorithms are introduced. However, the emergence and advancement of machine learning provide new options to address privacy and security concerns. Machine learning predicts the pattern of attacks that would occur in a network by analyzing past data that was generated in an IoT environment. Consequently, in this paper a number of machine learning models are employed to categorize the various types of IoT security assaults. Moreover, comparisons have demonstrated that machine learning models produce promising results.

The impact of computing on society is intricate and far-reaching both physically and virtually. Computers have led to an increase in productivity since they have made a wide variety of operations simpler and more efficient. Specifically, Internet of Things has made maintaining infrastructure faster, cheaper, and greener. When it comes to the relevance of the virtual world, technology has completely altered the way we engage with one another. Communication has been streamlined and quickened thanks to the internet and social media platforms. But along with the rising use of technology, new societal challenges are being witnessed including security, freedom, and privacy. Preserving these values is crucial for users, and machine learning may play a key role in mitigating these risks and challenges. This paper attempts to provide a machine learning strategy for safeguarding users' personal and sensitive data against intrusion, fraud, malware, spam, and fake profile, etc. Furthermore, the paper also presents the fruitful and encouraging results of various experiments based on proposed machine learning strategies while utilizing two separate datasets.

The IoT (Internet of Things) link system, various applications, data storage like cloud, and another service area that possibly will be a fresh entry for attackers as they uninterruptedly offer services in the organization. At this time, threats to users' privacy and malware pose significant challenges to the integrity of the Internet of Things. These extortions might lead to the loss of important information, which in turn could cause a company's finances and reputation to suffer. In this paper, we have identified anomalous activity throughout the IoT ecosystem by utilizing a variety of machine learning approaches. The results from the experiment indicate that the categorization capabilities of machine learning techniques may serve as an alternative strategy for ensuring the safety of communication inside the IoT.

The extensive use of Internet of Things (IoT) appliances has greatly contributed in the growth of smart cities. Moreover, the smart city deploys IoT-enabled applications, communications, and technologies to improve the quality of life, people's wellbeing, quality of services for the service providers and increase the operational efficiency. Nevertheless, the expansion of smart city network has become the utmost hazard due to increased cyber security attacks and threats. Consequently, it is more significant to develop the system models for preventing the attacks and also to protect the IoT devices from hazards. This paper aims to present a novel deep hybrid attack detection method. The input data is subjected for preprocessing phase. Here, data normalization process is carried out. From the preprocessed data, the statistical and higher order statistical features are extracted. Finally, the extracted features are subjected to hybrid deep learning model for detecting the presence of attack. The proposed hybrid classifier combines the models like Convolution Neural Network (CNN) and Deep Belief Network (DBN). To make the detection more precise and accurate, the training of CNN and DBN is carried out by using Seagull Adopted Elephant Herding optimization (SAEHO) model by tuning the optimal weights.

With the growth of the Internet of Things (IoT), security attacks are also rising gradually. Numerous centralized mechanisms have been introduced in the recent past for the detection of attacks in IoT, in which an attack recognition scheme is employed at the network’s vital point, which gathers data from the network and categorizes it as “Attack” or “Normal”. Nevertheless, these schemes were unsuccessful in achieving noteworthy results due to the diverse necessities of IoT devices such as distribution, scalability, lower latency, and resource limits. The present paper proposes a hybrid model for the detection of attacks in an IoT environment that involves three stages. Initially, the higher-order statistical features (kurtosis, variance, moments), mutual information (MI), symmetric uncertainty, information gain ratio (IGR), and relief-based features are extracted. Then, detection takes place using Gated Recurrent Unit (GRU) and Bidirectional Long Short-Term Memory (Bi-LSTM) to recognize the existence of network attacks. For improving the classification accuracy, the weights of Bi-LSTM are optimally tuned via a self-upgraded Cat and Mouse Optimizer (SU-CMO). The improvement of the employed scheme is established concerning a variety of metrics using two distinct datasets which comprise classification accuracy, and index, f-measure and MCC. In terms of all performance measures, the proposed model outperforms both traditional and state-of-the-art techniques.

Digital Forensics is a branch of forensic science that performs the task of data investigation, recovery and interpretation. The impact of the Internet of Things (IoT) can be seen everywhere now, but somehow it is quite difficult to identify the challenges posed by IoT criminals. It becomes possible to identify the offender of fraud attacks, cyber threats, security attacks, and computer frauds using digital forensics investigation mechanism. Numerous security challenges are faced in IoT enabled smart infrastructures. Digital forensic experts and law enforcement agencies can efficiently perform investigation processes in the cyber world. This paper provides a brief overview of IoT, its working, and need of digital forensics in an IoT enabled smart environment. In the present paper, vulnerabilities and cyber crimes existing in IoT environment also have been highlighted along with possible solutions. Various phases of digital forensics also have been discussed in the present paper.

Machine learning is being used in several aspects and revolutionized the method of believing.It is branch of Artificial Intelligence that takes input data for training the models.In present paper we focus on widely used model of machine learning i.e.Decision tree classifier and Logistics Regression, additionally tracking their performance along with their accuracy.Machine learning is emerging notion in IoT environment as security of IoT devices are crucial due to their resource constrained properties.

One of the most dynamic and invigorate advancement in information technology is advent of Internet of Things (IoT). IoT is territory of interrelated computational and digital devices with intelligence to transfer data. Along with swift expansion of IoT devices through the world security of things is not at expected height. As a consequence of ubiquitous nature of IoT environment most of the user do not have expertise or willingness to secure devices by themselves. Machine learning approach could be very effective to address security challenges in IoT environment. In recent related papers, the researcher have used machine learning techniques, approaches or methods for securing things in IoT environment. This paper attempts to review the related research on machine learning approaches to secure IoT devices.

IoT (Internet of Thing) is becoming ubiquitous day by day and making dumb devices smarter by enabling them to transfer the information over the network. IoT not confined to homes or in utilities but can be found in array of fields. IoT is rapidly making the world smarter by connecting physical to digital world and it is estimated that by 2024 more than 20 billion devices are likely to be connected. It brings opportunity but also brings numerous kind of risks. The worry is how we to keep billions of devices secure and what to ensure the security of networks these run on. The present paper focused on all the issues concerning about securing IoT environment and how machine learning techniques may help to address these security issues. The paper also discusses the proposed approaches, parameters, characteristic of techniques and explores which technique could be more effective.