Current techniques for multi-pose human face matching yield suboptimal outcomes because of the intricate nature of pose equalization and face rotation. Deep learning models, such as YOLO-V5, etc., that have been proposed to tackle these complexities, suffer from slow frame matching speeds and therefore exhibit low face recognition accuracy. Concerning this, certain literature investigated multi-pose human face detection systems; however, those studies are of elementary level and do not adequately analyze the utility of those systems. To fill this research gap, we propose a real-time face matching algorithm based on YOLO-V5. Our algorithm utilizes multi-pose human patterns and considers various face orientations, including organizational faces and left, right, top, and bottom alignments, to recognize multiple aspects of people. Using face poses, the algorithm identifies face positions in a dataset of images obtained from mixed pattern live streams, and compares faces with a specific piece of the face that has a relatively similar spectrum for matching with a given dataset. Once a match is found, the algorithm displays the face on Google Colab, collected during the learning phase with the Robo-flow key, and tracks it using the YOLO-V5 face monitor. Alignment variations are broken up into different positions, where each type of face is uniquely learned to have its own study demonstrated. This method offers several benefits for identifying and monitoring humans using their labeling tag as a pattern name, including high face-matching accuracy and minimum speed of owing face-to-pose variations. Furthermore, the algorithm addresses the face rotation issue by introducing a mixture of error functions for execution time, accuracy loss, frame-wise failure, and identity loss, attempting to guide the authenticity of the produced image frame. Experimental results confirm effectiveness of the algorithm in terms of improved accuracy and reduced delay in the face-matching paradigm.

In recent years, there is an exponential explosion of data generation, collection, and processing in computer networks. With this expansion of data, network attacks have also become a congenital problem in complex networks. The resource utilization, complexity, and false alarm rates are major challenges in current Network Intrusion Detection Systems (NIDS). The data fusion technique is an emerging technology that merges data from multiple sources to form more certain, precise, informative, and accurate data. Moreover, most of the earlier intrusion detection models suffer from overfitting problems and lack optimal detection of intrusions. In this paper, we propose a multi-source data fusion scheme for intrusion detection in networks (MIND) , where data fusion is performed by the horizontal emergence of two datasets. For this purpose, the Hadoop MapReduce tool such as, Hive is used. In addition, a machine learning ensemble classifier is used for the fused dataset with fewer parameters. Finally, the proposed model is evaluated with a 10-fold-cross validation technique. The experiments show that the average accuracy, detection rate, false positive rate, true positive rate, and F-measure are 99.80%, 99.80%, 0.29%, 99.85%, and 99.82% respectively. Moreover, the results indicate that the proposed model is significantly effective in intrusion detection compared to other state-of-the-art methods.

The biggest challenge for symmetric cryptosystems is to replace their static substitution with dynamic substitution, because static substitution S-boxes make the symmetric block ciphers more vulnerable to attacks. Previous well-known dynamic key-dependent S-boxes are lacking in dynamicity and do not provide optimal security for symmetric block ciphers. Therefore, this research aims to contribute an effective and secure method for designing key-dependent dynamic S-box with dynamic permutations to make the symmetric block ciphers optimally secure. The proposed S-box method has been experimentally evaluated through several measures such as bit independence criteria, non-linearity, hamming distance, balanced output, strict avalanche criteria including differential and linear approximation probabilities. Moreover, the randomness properties of proposed method have also been evaluated through several standard statistical tests as recommended by the National Institute of Standards and Technology (NIST). Thus, the results show that the proposed method, not only retains effective randomness properties but it also contains, good avalanche effect (up to 62.32%) which is significantly improved than others. Therefore, the proposed substitution method is highly sensitive to the secret key because, only a single bit change in key generates an entirely new S-box with all 256 values at different positions. Thus, the overall evaluation shows that the proposed substitution method is optimally secure and outperforming as compared to the existing S-box techniques. In future, the proposed method can be extended for different key sizes (192–256 bits) or even more.

Traditional cryptographic methods often need complex designs that require substantial memory and battery power, rendering them unsuitable for small handheld devices. As the prevalence of these devices continues to rise, there is a pressing need to develop smart, memory-efficient cryptographic protocols that provide both high speed and robust security. Current solutions, primarily dependent on dynamic permutations, fall short in terms of encryption and decryption speeds, the cryptographic strength, and the memory efficiency. Consequently, the evolution of lightweight cryptographic algorithms incorporating randomised substitution properties is imperative to meet the stringent security demands of handheld devices effectively. In this paper, we present an advanced design of lightweight block ciphers that enhances traditional dynamic permutations with innovative randomised substitutions. This design utilises straightforward randomized encryption methods such as XOR, nibble swap, count ones, and left shift. The cryptographic robustness of our proposed block cipher has been rigorously tested through several standardised statistical tests, as recommended by the National Institute of Standards and Technology (NIST). These evaluations confirm that our algorithm maintains strong cryptographic properties with randomised substitutions and outperforms existing models in several key aspects. Moreover, comparative assessments reveal that our algorithm achieves a throughput of 853.31 Kbps while consuming only 1510 bytes of memory and demonstrating over 60% avalanche properties, significantly outperforming other solutions in terms of CPU utilisation and memory consumption. These results underscore the efficacy of our approach in fulfilling the advanced security requirements of modern handheld devices.