Vision impairment affects an individual’s quality of life, posing challenges for visually impaired people (VIPs) in various aspects such as object recognition and daily tasks. Previous research has focused on developing visual navigation systems to assist VIPs, but there is a need for further improvements in accuracy, speed, and inclusion of a wider range of object categories that may obstruct VIPs’ daily lives. This study presents a modified version of YOLOv4_Resnet101 as backbone networks trained on multiple object classes to assist VIPs in navigating their surroundings. In comparison to the Darknet, with a backbone utilized in YOLOv4, the ResNet-101 backbone in YOLOv4_Resnet101 offers a deeper and more powerful feature extraction network. The ResNet-101’s greater capacity enables better representation of complex visual patterns, which increases the accuracy of object detection. The proposed model is validated using the Microsoft Common Objects in Context (MS COCO) dataset. Image pre-processing techniques are employed to enhance the training process, and manual annotation ensures accurate labeling of all images. The module incorporates text-to-speech conversion, providing VIPs with auditory information to assist in obstacle recognition. The model achieves an accuracy of 96.34% on the test images obtained from the dataset after 4000 iterations of training, with a loss error rate of 0.073%.

Recently, on social media, various kinds of social engineering (SE) have made individuals more susceptible to attacks. A phishing attempt is a widely used SE technique that takes advantage of people’s vulnerabilities to acquire personal or confidential information. These attempts are growing at an astonishing speed, causing harm to both individuals and corporations. According to the latest studies, certain individuals are more vulnerable to such kinds of attacks than others. However, the relationship between psychological characteristics and phishing attacks has not been adequately investigated. This study empirically explores the connection between phishing vulnerability that causes data biases and the Big Five personality traits. Recognizing personality traits that make people more vulnerable to phishing attempts is a key step in developing protection and safeguarding individuals. The individuals who scored high in some traits are more probable to suffer from such assault. To the best of our knowledge, no prior quantitative study has attempted to find many genuine phishing victims and their personality behavior. This problem lacks the availability of publically accessible data. It is also challenging to estimate the probability distribution of rows in tabular data and generate realistic synthetic data to train/test the model on more data. This work employs a conditional generative adversarial network (C-GAN) for both data generation and classification to find the correlation between personality traits and phishing attacks.