SACM - United Kingdom
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9667
Browse
3 results
Search Results
Item Restricted Credit Card Fraud Prediction Using Machine Learning Model(University of Essex, 2024-08) Alanazi, Mohammed; Walton, MichaelThe widespread adoption of credit cards has significantly increased the frequency of fraudulent activities. This has resulted in considerable financial losses for both consumers and financial institutions. As the use of credit cards continues to grow, the challenge of protecting transactions against unauthorized access has become more serious than ever. This research focuses on creating a solution using machine learning to accurately and effectively identify fraudulent credit card transactions. It addresses the issue of uneven transaction data by employing advanced methods such as logistic regression, XGBoost, LightGBM, and a hybrid model. The research involves thorough data preparation, model development, and careful assessment using measures “such as accuracy, precision, recall, F1 score, and ROC AUC”. This research leverages sophisticated machine learning techniques and tackles the specific challenges associated with imbalanced data. The study aims to significantly enhance the detection of fraudulent transactions while reducing false positives. The ultimate goal is to boost the security of financial systems, thus providing better protection against fraud, and to improve trust and reliability in credit card transactions.44 0Item Restricted Utilizing Data Analytics for Fraud Detection and Prevention in Online Banking Systems of Saudi Arabia(University of Portsmouth, 2024-09) Almotairy, Yazeed; Jiacheng, TanThis thesis addresses the critical issues of online banking and online banking fraud in Saudi Arabia. The thesis focusses on the older methodologies of the online banking systems in Saudi Arabia. The frauds are discussed in detail that are occurring in the online banking systems and are causing inconvenience to the users and account holders of the online banks and applications. In this thesis, online banking frauds are discussed thoroughly, and the traditional fraud detection methods are elaborated as well. The vulnerabilities in the current systems are explored. It discusses how the older systems are not performing well and why the new system encompasses the power of data analytics and machine learning. The methods proposed use a set of data analytics and machine learning algorithms and techniques to detect fraud or any fraudulent activity that a scammer or fraudster may perform. The results of this study explain how the proposed system can outperform the traditional methodologies being used in Saudi Arabian online banking systems. The proposed system can also enhance the user experience. The possible privacy and ethical concerns are also discussed. In the end, it is also discussed what the future prospects are for the researchers who are looking to enhance this research or want to work in the field of data analytics and machine learning to improve the security of the security of online banking applications. In conclusion, this thesis not only contributes to the body of knowledge on online banking frauds in Saudi Arabia and their detection but also features future research topics for new researchers.14 0Item Restricted Anomaly Detection in Face Anti-spoofing: Algorithms, Training Set Construction, and Bias Analysis(Durham University, 2023-12-07) Abduh, Latifah Abdullah A; Lvrissimtzis, LoannisFace recognition is a mature and trustworthy method for identifying individuals. Thanks to the availability of high-definition cameras and accompanying devices, this particular biometric recognition modality is widely regarded as the fastest and least obtrusive option. Despite advancements in face recognition systems, it has been discovered that successful spoofing attempts are still possible. Various anti-spoofing algorithms, also known in the literature as liveness detection tests and presentation attack detection algorithms, have been devised to counteract such attacks. The first contribution of this research is to demonstrate the effectiveness of certain simple and direct spoofing attacks. Our approach involves utilizing ResNet50, a highly reliable deep neural network, as a binary classification method. We assess its performance by subjecting it to adversarial attacks that involve manipulating the saturation component of imposter images. We have found that it is particularly vulnerable to spoofing attacks that employ processed imposter images. To the best of our knowledge, this study represents the pioneering exploration of adversarial attacks on deep neural networks within the realm of face anti-spoofing detection. In addition, we conducted an experiment that revealed the potential of the proposed adversarial attack to be converted into a direct presentation attack. In a second contribution, we propose an alternative approach incorporating in the- wild images and non-specialised databases into anomaly detection to improve the face anti-spoofing algorithm’s performance on unseen databases. We developed a method for detecting anomalies in face anti-spoofing by employing a convolutional autoencoder. We assessed its effectiveness using the NUAA database, which had not been previously utilized in the training. Our results indicated improved performance when incorporating in-the-wild face images and face data from nonspecialized databases into the training dataset. Transformers are emerging as the new gold standard in various computer vision applications and have already been used in face anti-spoofing, demonstrating competitive performance. In a third contribution, we propose a network with the ViT transformer and ResNet18 as the backbone for anomaly detection in face anti-spoofing with a decoder as the head. Then, we validate various anomaly detectors to compare the results with our proposed method. Also, using the ViT with MLP as a binary classifier baseline and compare it with our model. Our comprehensive testing and evaluation have demonstrated that this proposed approach competes admirably as a method for detecting anomalies in the domain of face anti-spoofing. Finally, there are only a few papers that specifically address the issue of racial bias in anti-spoofing. As a fourth contribution, we present a systematic study of race bias in face anti-spoofing with three key characteristics: the focus is on analysing potential bias in bona fide errors, where significant ethical and legal issues lie; analyses of various stages of the classification process, and treating the value of the threshold that determines the classifier’s operating point on the ROC curve as a user-defined variable. We do not assume it is fixed by the vendor of the biometric verification system through a black-box process. To the best of our knowledge, this is the first investigation into racial bias within the face anti-spoofing domain that employs anomaly detection techniques while also incorporating a non-specialized database for analysis. Our results show that racial bias in face anti-spoofing is influenced by factors beyond mean response values, such as different variances, bimodality, and outliers. Overall, this thesis contributes to the ongoing development of anti-spoofing techniques and investigates some important issues regarding the potential for bias in these systems.10 0