The banking and financial sector has always been a prime target for cyber threats due to the critical nature of the information they handle. With the increasing dependence on technology and digital transformation, the sector is facing more complex and sophisticated threats from cybercriminals. The banking sector serves as the backbone of a country’s economy, interlinked with various other sectors like petroleum, mining, health, and industry. Any significant damage to the banking sector can send shockwaves through the entire economic landscape. Therefore, cyber threat classifications play a crucial role in risk management and provide a valuable framework for understanding and responding to cyber threats. Understanding the potential impact of a cyber-attack helps organisations assess the risks they face and develop appropriate risk mitigation strategies. The purpose of this research paper is to provide a comprehensive analysis of cyber threats in the banking and financial sectors, including identifying common threats, their nature and character to help in classification. One of the significant contributions of this research paper is to classify cyber threats to the banking and financial sectors based on their severity and technicality. This classification helps to identify the appropriate countermeasures required to mitigate the risks of each type of threat. Furthermore, the paper explores the technical, non-technical, organizational countermeasures and the legal and regulatory measures used to protect financial transactions from cyber threats. This research work delves into the challenges and limitations of cyber threat classifications, focusing specifically on those confronting the banking and financial sector in their pursuit of robust cybersecurity. Additionally, it analyses recent trends and developments in the field, highlighting the evolving nature of cyber threats to banking. The most significant challenge is the rapidly evolving nature of cyber threats, making it challenging to keep up with the latest trends and technologies.

Intrusion Detection Systems (IDS) are vital for protecting networks with evolving cyber threats, that comprises malware, denial-of-service attacks, and botnets. Hence, this study proposes a novel hybrid deep learning model, which associates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), along with a self-attention method to highlight the utmost informative input features. Here, CNN works with extraction of spatial features, LSTM works with modelling of temporal sequence. The proposed model is termed Attention-CNN-LSTM. The proposed model achieves 94.8–97.5% accuracy and significantly improves Matthews Correlation Coefficient (MCC) and F1-score by evaluating on NSL-KDD and Bot-IoT datasets. An ablation study confirms each component contribution, particularly the attention layer, to overall performance gains. The architecture supports real-time inference with sub-35ms latency. The model also shows strong potential for real-time deployment, processing over 1200 records per second; hence, this work is applicable for high-traffic environments.

Cybersecurity in the Internet of Things (IoT) ecosystem is vital to protect sensitive data, stop unauthorized access, and mitigate the risk of disruptive cyberattacks. Mitigating risks in IoT devices and networks through encryption, authentication protocols, and continuous monitoring is paramount to ensure the privacy, reliability, and entire safety of connected systems, raising the wide support and success of IoT technologies. Cyberattack recognition utilizing an intrusion detection system (IDS) is a major imperative given the increase in the number of connected devices. Advanced cybersecurity methods deploy machine learning (ML) approaches, anomaly detection, and behavioral analysis to analyze IoT network traffic for irregular patterns indicative of potential cyberattacks. The combination of feature selection (FS) and deep learning (DL) approaches in cyberattack recognition suggests a proactive and sophisticated manner to bolster cybersecurity. Leveraging DL structures like neural networks (NNs) assists the automatic extraction and analysis of intricate patterns in the difficult IoT data landscape. This synergy develops the accuracy and performance of cyberattack recognition, as the system learns to detect normal device behavior from anomalies. This paper develops an Improved Mayfly Optimization Algorithm with a Hybrid Deep Learning based Intrusion Detection (IMFOHDL-ID) approach in IoT environments. The designed IMFOHDL-ID approach’s main goal is to classify intrusions and accomplish security in the IoT environment. The IMFOHDL-ID technique initially follows data normalization as a preprocessing stage. In addition, the IMFOHDL-ID technique makes use of the IMFO-based feature selection (FS) method to elect feature subsets. For IDs, the IMFOHDL-ID technique applies the Long Short Term Memory based Deep Stacked Sequence-to-Sequence Autoencoder (LSTM-DSSAE) model. Finally, the dipper-throated optimization algorithm (DTOA) was utilized for optimal hyperparameter selection of the LSTM-DSSAE method. To highlight better results of the IMFOHDL-ID model, a series of simulation analyses were performed. Extensive comparative results stated the improved outcome of the IMFOHDL-ID technique over existing approaches.

This study presents a novel Similarity-Based Hybrid API Malware Detection Model (HAPI-MDM) aiming to enhance the accuracy of malware detection by leveraging the combined strengths of static and dynamic analysis of API calls. Faced with the pervasive challenge of obfuscation techniques used by malware authors, the conventional detection models often struggle to maintain robust performance. Our proposed model addresses this issue by deploying a two-stage learning approach where the XGBoost algorithm acts as a feature extractor feeding into an Artificial Neural Network (ANN). The key innovation of HAPI-MDM is the similarity-based feature, which further enhances the detection accuracy of the dynamic analysis, ensuring reliable detection even in the presence of obfuscation. The model was evaluated using seven machine learning techniques with 10 K-fold cross-validation. Experimental results demonstrated HAPI-MDM’s superior performance, achieving an overall accuracy of 97.91% and the lowest false-positive and false-negative rates compared to related works. The findings suggest that integrating dynamic and static API-based features and utilizing a similarity-based feature significantly improves malware detection performance, thereby offering an effective tool to fortify cybersecurity measures against escalating malware threats.

The security of IoT networks has become a significant concern owing to the increasing count of cyber threats. Traditional Intrusion Detection Systems (IDS) struggle to detect sophisticated attacks in real-time due to resource constraints and evolving attack patterns. This study proposes a novel IDS that integrates deep learning (DL) and machine learning (ML) approaches to improve IoT security. The main objective is to develop a hybrid IDS combining Feed Forward Neural Networks (FFNN) and XGBoost to improve attack detection accuracy while minimizing computational overhead. The proposed methodology involves data preprocessing, feature selection utilizing Principal Component Analysis (PCA), and classification employing FFNN and XGBoost. The model is trained and evaluated on the CIC IoT 2023 dataset, which comprises real-time attack data, ensuring its practical relevance. The proposed model is estimated on the CIC IoT 2023 dataset, demonstrating superior accuracy (99%) compared to existing IDS techniques. This study provides valuable insights into improving IDS models for IoT security, addressing challenges such as dataset imbalance, feature selection, and classification accuracy. Results demonstrate that the hybrid FFNN-XGBoost model outperforms standalone FFNN and XGBoost classifiers, achieving an accuracy of 99%. Compared to existing IDS models, the proposed approach significantly enhances precision, recall, and F1-score, ensuring robust intrusion detection. This research contributes to IoT security by introducing a scalable and efficient hybrid IDS model. The findings offer a strong basis for future advancements in intrusion detection using DL and ML approaches.

Secure storage model for digital forensics represents essential progress in the domain, addressing the major problems associated with protecting and maintaining digital evidence. This method employs recent encryption systems and optimal key generation methods to ensure the confidentiality and integrity of data throughout the investigative process. Cloud forensics is an intelligent development of digital forensics to be preserved against online hacking. But, centralized evidence gathered and preservation reduces the reliability of digital evidence. The architecture for digital forensics in an Infrastructure as a Service (IaaS) cloud platform is a crucial structure intended to simplify the collection and protection of evidence while preserving the integrity and origin of digital objects within cloud-based methods. This architecture integrates numerous modules and methods to address the exclusive tasks modeled by cloud computing (CC) environments in the framework of forensic investigations. This paper develops a new digital forensic architecture utilizing the Authentication with Optimal Key Generation Encryption (DFA-AOKGE) technique. The main intention of the DFA-AOKGE method is to use a BC-distributed design to allocate data between numerous peers for data collection and safe storage. Additionally, the DFA-AOKGE model uses the Secure Block Verification Mechanism (SBVM) for the authentication procedure. Also, the secret keys can be produced by the usage of the Enhanced Equilibrium Optimizer (EEO) model. Furthermore, the encryption of the data takes place using a multikey homomorphic encryption (MHE) approach and is then saved in the cloud server. The simulation value of the DFA-AOKGE methodology takes place in terms of different aspects. The simulation results exhibited that the DFA-AOKGE system shows prominent performance over other recent approaches in terms of different measures.