Atta Ur Rehman Khan

Twitter is considered a useful tool for effective tracking and management of crisis-related incidents. However, due to a large number of irrelevant features in textual data, the problem of high dimensionality arises which eventually increases the computational cost and also decreases the classification performance. Thus to handle such type of problem, this work presents Spark based hybrid binary Bat (BBA) and binary Salp swarm algorithm (BSSA) named as SBBASSA for feature selection and classification of crisis-related tweets. In the proposed technique at first, the hybridization of standard BBA and BSSA algorithms is performed to enhance their exploration capabilities, then the combined algorithm is implemented in parallel using Apache Spark framework to reduce the overall execution time during the feature selection process. A support vector machine (SVM) classifier is applied during the wrapper-based feature subset selection and classification process. The performance of the proposed SBBASSA was analyzed on six benchmark crisis tweet datasets, namely Hurricane Sandy, Boston Bombings, Oklahoma Tornado, West Texas Explosion, Alberta Floods, and Queensland Floods, and then compared with standard BSSA, BBA, and binary particle swarm optimization (BPSO). Results showed that SBBASSA performed competently in the feature selection and classification process, as well as outperforming other algorithms in crisis tweet classification, and achieved the highest accuracy with the lowest feature set in a reduced execution time.

The Internet of Things (IoT) is transforming how we live and work, and its applications are widespread, spanning smart homes, industrial monitoring, smart cities, healthcare, agriculture, and retail. Considering its wide range of applications, addressing the security challenges arising from IoT devices’ massive collection and transmission of user data is vital. Intrusion detection systems (IDS) based on deep learning techniques offer new means and research directions for resolving IoT security issues. Deep learning models can process large volumes of data and extract complex patterns, making them generally more effective than traditional rule based IDSs. While deep learning techniques are gradually gaining popularity in IDS applications, current research needs a comprehensive summary of deep learning-based IDS in IoT. This paper introduces intrusion detection technologies, followed by a detailed comparison, analysis, and discussion of deep learning models, datasets, feature extraction and classifiers, data preprocessing techniques, and experimental design of the models. It also highlights the challenges and issues associated with deep learning models and relevant techniques for IDS. Finally, it concludes by providing recommendations to assist researchers in this domain.

Ensuring the security of critical Industrial Internet of Things (IIoT) systems is of utmost importance, with a primary focus on identifying cyber-attacks using Intrusion Detection Systems (IDS). Deep learning (DL) techniques are frequently utilized in the anomaly detection components of IDSs. However, these models often generate high false-positive rates, and their decision-making rationale remains opaque, even to experts. Gaining insights into the reasons behind an IDS’s decision to block a specific packet can aid cybersecurity professionals in assessing the system’s effectiveness and creating more cyber-resilient solutions. In this paper, we offer an explainable ensemble DL-based IDS to improve the transparency and robustness of DL-based IDSs in IIoT networks. The framework incorporates Shapley additive explanations (SHAP) and Local comprehensible-independent Clarifications (LIME) methods to elucidate the decisions made by DL-based IDSs, providing valuable insights to experts responsible for maintaining IIoT network security and developing more cyber-resilient systems. The ToN_IoT dataset was used to evaluate the efficacy of the suggested framework. As a baseline intrusion detection system, the extreme learning machines (ELM) model was implemented and compared with other models. Experiments show the effectiveness of ensemble learning to improve the results.

Parkinson’s Disease (PD) in the set of neuro-degenerative disorders stimulates due to the loss of dopaminergic neurons from the substantia nigra. Electroencephalogram (EEG) signals are being extensively utilized for diagnosing PD. The existing approaches extract the features using various frequency transformations that lose valuable signal information. An optimized Deep Convolutional Neural Network (CNN) inspired by the encoder part of U-Net architecture is proposed for classifying PD incorporating the resting electroencephalogram (EEG) signal dataset. The proposed model follows the U-Net architecture for extracting the features from the signals. The EEG recordings are taken from two datasets: the University of Mexico (UNM) EEGs and the University of California San Diego (UCSD) resting state dataset. The EEGs are pre-processed with a basic pre-processing pipeline, which is then separated into single channels, plotting each channel as a simple graph. These graphs are then fed to the proposed 23-layered convolutional neural network (CNN) for classifying PD from the normal control. Consequently, the model achieved maximum values of 93.10%, 93.18%, 93.09%, and 0.9313 of accuracy, precision, recall, and F1-score respectively for the UNM dataset, whereas, 97.90%, 98%, 97.87% and 0.9794 of accuracy, precision, recall, and F1-score respectively for UCSD dataset. The results show improved scores compared to the Machine Learning and CNN models applied on the same datasets individually.

Advanced Persistent Threat is an attack campaign in which an intruder or team of intruders establishes a long-term presence on a network to mine sensitive data, which becomes more dangerous when combined with polymorphic malware. This type of malware is not only undetectable, but it also generates multiple variants of the same type of malware in the network and remains in the system’s main memory to avoid detection. Few researchers employ a visualization approach based on a computer’s memory to detect and classify various classes of malware. However, a preprocessing step of denoising the malware images was not considered, which results in an overfitting problem and prevents us from perfectly generalizing a model. In this paper, we introduce a new data engineering approach comprising two main stages: Denoising and Re-Dimensioning. The first aims at reducing or ideally removing the noise in the malware’s memory-based dump files’ transformed images. The latter further processes the cleaned image by compressing them to reduce their dimensionality. This is to avoid the overfitting issue and lower the variance, computing cost, and memory utilization. We then built our machine learning model that implements the new data engineering approach and the result shows that the performance metrics of 97.82% for accuracy, 97.66% for precision, 97.25% for recall, and 97.57% for f1-score are obtained. Our new data engineering approach and machine learning model outperform existing solutions by 0.83% accuracy, 0.30% precision, 1.67% recall, and 1.25% f1-score. In addition to that, the computational time and memory usage have also reduced significantly.

In the Internet of Battlefield Things (IoBT), users and sensor-equipped entities send multiple messages to the Command Control Center (CCC) over the network. The authentication and integrity of these messages are crucial because if an adversary or malicious node transmits, alters, or replays these messages, the consequences will be disasters. Current centralized authentication systems are not suitable for the distributed environment because such schemes are prone to a single point of failure, privacy, and scalability issues. Moreover, the high communication overhead caused by centralization increases energy consumption. In this work, we propose a technique called Blockchain-based Autonomous Authentication and Integrity for the Internet of Battlefield Things (BIoBT) for the C3I system. The proposed technique does not require an explicit authentication channel for the authentication of entities because it is performed on the blockchain side when receiving the data. In addition, it provides data integrity and non-repudiation. BIoBT prototype is created, deployed, and tested on the Ethereum test network. The results prove that BIoBT is efficient, cost-effective, and satisfies the security requirements of a distributed environment for IoBT. BIoBT also outperforms contemporary mechanisms in terms of the number of messages required to establish a secure channel, reducing communication overhead and resource consumption.

Malware has recently grown exponentially in recent years and poses a serious threat to individual users, corporations, banks, and government agencies. This can be seen from the growth of Advanced Persistent Threats (APTs) that make use of advance and sophisticated malware. With the wide availability of computer-automated tools such as constructors, email flooders, and spoofers. Thus, it is now easy for users who are not technically inclined to create variations in existing malware. Researchers have developed various defense techniques in response to these threats, such as static and dynamic malware analyses. These techniques are ineffective at detecting new malware in the main memory of the computer and otherwise require considerable effort and domain-specific expertise. Moreover, recent techniques of malware detection require a long time for training and occupy a large amount of memory due to their reliance on multiple factors. In this paper, we propose a computer vision-based technique for detecting malware that resides in the main computer memory in which our technique is faster or memory efficient. It works by taking portable executables in a virtual environment to extract memory dump files from the volatile memory and transform them into a particular image format. The computer vision-based contrast-limited adaptive histogram equalization and the wavelet transform are used to improve the contrast of neighboring pixel and to reduce the entropy. We then use the support vector machine, random forest, decision tree, and XGBOOST machine learning classifiers to train the model on the transformed images with dimensions of 112 × 112 and 56 × 56. The proposed technique was able to detect and classify malware with an accuracy rate of 97.01%. Its precision, recall, and F1-score were 97.36%, 95.65%, and 96.36%, respectively. Our finding shows that our technique in preparing dataset with more efficient features to be trained by the Machine Learning classifiers has resulted in significant performance in terms of accuracy, precision, recall, F1-score, speed and memory consumption. The performance has superseded most of the existing techniques in its unique approach.

Recycling of electronic waste is a rapidly growing global issue that requires proper monitoring and tracing of electronic devices and the business transactions between the stakeholders. The majority of current systems that manage electronic devices throughout their supply chain stages are centralized and lack data transparency, immutability, and security. Specifically, such systems are incapable of handling problems like comprehensive coverage of the life cycle of e-products, access control for maintaining data security, reputation-aware selection of stakeholders, and large amounts of data generated during various stages of the supply chain processes. In this paper, we propose a blockchain-based IoT-enabled system for monitoring all post-production business processes, activities, and operations performed on an electronic device. The system is supported by five smart contracts that record the actions of users on the immutable distributed ledger that aid in ensuring that the business processes carried out by the participants are transparent, traceable, and secure. To store large files, such as images of e-waste materials, products, and licenses for stakeholders, we have integrated our system with a distributed storage system. The proposed system is tested on Ethereum blockchain to check the gas consumption of the functions of the smart contracts. The cost and security analysis shows that the proposed system is viable.