Detection of anomalies in video surveillance plays a key role in ensuring the safety and security of public spaces. The number of surveillance cameras is growing, making it harder to monitor them manually. So, automated systems are needed. This change increases the demand for automated systems that detect abnormal events or anomalies, such as road accidents, fighting, snatching, car fires, and explosions in real-time. These systems improve detection accuracy, minimize human error, and make security operations more efficient. In this study, we proposed the Composite Recurrent Bi-Attention (CRBA) model for detecting anomalies in surveillance videos. The CRBA model combines DenseNet201 for robust spatial feature extraction with BiLSTM networks that capture temporal dependencies across video frames. A multi-attention mechanism was also incorporated to direct the model’s focus to critical spatiotemporal regions. This improves the system’s ability to distinguish between normal and abnormal behaviors. By integrating these methodologies, the CRBA model improves the detection and classification of anomalies in surveillance videos, effectively addressing both spatial and temporal challenges. Experimental assessments demonstrate that the CRBA model achieves high accuracy on both the University of Central Florida (UCF) and the newly developed Road Anomaly Dataset (RAD). This model enhances detection accuracy while also improving resource efficiency and minimizing response times in critical situations. These advantages make it an invaluable tool for public safety and security operations, where rapid and accurate responses are needed for maintaining safety.

Surveillance cameras have been widely used for monitoring in both private and public sectors as a security measure. Close Circuits Television (CCTV) Cameras are widely used to surveillance normal and anomalous incidents. Real-world anomaly detection in complex environment situations is a significant challenge due to its diverse nature manually reviewing this vast data is difficult, time-consuming, and prone to errors. Human operators may overlook crucial information due to failure, which reduces the accuracy of manual monitoring. This highlights the need for automated solutions to improve accuracy and efficiency We proposed a Bidirectional Motion Temporal (BiMT) model to address this issue by coupling a pre-trained model of deep neural networks. This system utilizes a Convolutional Neural Network (CNN) to extract the best spatial key features from the video stream, which are converted into time series data and coupled with Recurrent Neural Network (RNN) deep learning model Bidirectional Long Short-Term Memory (BiLSTM) extract temporal key features, and Multi-Head Self-Attention (MHSA) allows for the detection of short-term frame correlations. In addition, created a custom transformer encoder with relative positional embedding that improves the detection and recognizes long-range frame dependencies. Furthermore, categorical focal loss (CFL) is used during training to prioritize essential features and further enhance the model's precision. The more sophisticated ConvNeXtv2 model produced average AUC scores of 98.6%, 86.5%, and 83.5% for the UCF-Crime, UBI-Fight, and RAD datasets respectively.

DDoS (Distributed Denial-of-Service) attacks are significant cyber threats that affect network infrastructures and cause massive service disruption. DDoS attacks have become even more threatening, owing to the poor security of IoT devices. This paper proposes two ensemble approaches: (1) Optimized Ensemble Stacking Approach 4 (OESA-4) and (2) Optimized Ensemble Voting Approach 4 (OEVA-4). Both proposed approaches use four supervised machine learning classifiers, such as K-Nearest Neighbors (KNN), Random Forest (RF), Extreme Gradient Boosting (XGB), and Decision Tree (DT). OESA-4 combines the base learners’ outputs via a meta-learner, and OEVA-4 uses weighted soft-voting, assigning different weights to base learners to improve the output’s efficiency. An experimental analysis was conducted on a subset of the CIC-DDoS2019 dataset offered by the Canadian Institute for Cybersecurity to test the performance of state-of-the-art classifiers and proposed approaches. This subset of the dataset contains 325,965 occurrences. The results show that the proposed OESA-4 and OEVA-4 demonstrated reliable performance with accuracies of 99.87% and 99.73%, respectively, on a single split, whereas stratified five-fold cross-validation resulted in mean accuracies of 99.51% ± 0.08% for OESA-4 and 99.28% ± 0.11% for OEVA-4 respectively. The relatively low errors in both cases are indicative of consistent performance in all the five folds tested, demonstrating strong and consistent classification capabilities within the experiments. Thus, the presented paper shows that OESA-4 and OEVA-4 approaches achieve higher performance in identifying various types of DDoS attacks compared to individual classifiers.