Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
2 results
Search Results
Item Restricted Novel Deepfakes Detection Strategies: Insights from Prosopagnosia(Newcastle University, 2024-10) Alanazi, Fatimah; Morgan, GrahamThe credibility of audio and video content, which is essential to our perception of reality, is increasingly challenged by advancements in deepfake generation techniques. Existing detection models primarily focus on identifying anomalies and digital artifacts. However, the rapid evolution of technology enables the creation of sophisticated deepfakes that can evade these methods. This thesis investigates the effectiveness of different facial features for deepfake detection in images and face recognition in individuals with prosopagnosia. It examines whether there is a correlation between the facial features prioritized by AI models for deepfake detection and those emphasized in training programs aimed at enhancing face recognition in individuals with prosopagnosia. Additionally, it assesses the impact of occluding each facial feature during training on AI model performance and identifies which facial elements individuals with prosopagnosia find most challenging to recognize. Inspired by research into prosopagnosia, which highlights the importance of internal facial features like the eyes and nose, this study proposes a novel approach to deepfake detection. The methodology involves identifying critical facial features, applying face cut-out techniques to create training images with various occlusions, and evaluating AI models trained on these datasets using EfficientNet-B7 and Xception models. The results indicate that models trained with occluded datasets performed better, with the EfficientNet-B7 model achieving a higher accuracy rate (92%) when core facial elements (eyes and nose) were covered, compared to models trained on datasets without occlusions or with occlusions covering external features. This suggests that focusing on features outside the face’s center improves detection accuracy. The findings also highlight that facial cues beneficial for individuals with prosopagnosia do not uniformly translate to equivalent value for AI models. This research demonstrates that detection systems can be more effective by focusing on a small region of the face, contributing significantly to the improvement of deepfake detection methods and enhancing our understanding of face recognition processes.22 0Item Restricted Machine Learning (ML) Technologies(John Jay College of Criminal Justice, 2024-04-03) Alanazi, Mosa; Seferaj, GentianaIntegrating Machine Learning (ML) technologies into physical security has ignited significant discourse within scholarly circles, focusing on identifying specific ML technologies currently employed and elucidating their tangible outcomes. This integration occurs against a rapidly evolving technological landscape, encompassing advancements such as cloud computing, 5G wireless technology, real-time Internet of Things (IoT) data, surveillance cameras fortified with biometric technologies, and predictive data analytics. Collectively, these innovations augment the transformative potential of ML within security frameworks, ranging from sophisticated video analytics facilitating advanced threat detection to predictive algorithms aiding in comprehensive risk assessment. Moreover, the seamless fusion of disparate data streams and the capability to extract actionable insights in real-time present profound implications for the future trajectory of security protocols, heralding a paradigm shift in the conceptualization, implementation, and Student No: 10001 Page 2 of 14 Comprehensive Exam/Project ̶̶̶ Spring24 Department of Security, Fire and Emergency Management maintenance of physical security measures. This study endeavors to delve into the specifics of ML technologies currently operationalized in physical security contexts, scrutinize the tangible outcomes they yield, and forecast how these trends will shape the future security landscape— additionally, strategic recommendations aimed at optimizing the efficacy of ML-driven security solutions in safeguarding physical environments.127 0