[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128201-en":3,"doc-seo-128201-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128201,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","A Hybrid Approach to Machine Learning-Based Deepfake Video Detection - Masters Thesis","The thesis investigates deepfake video manipulation driven by generative AI, where face replacement and copied facial movements can produce highly realistic yet fraudulent footage. It addresses risks to security, misinformation, and personal privacy by developing an effective detection system. Using the publicly available UADFV deepfake dataset, the research proposes a hybrid machine-learning model that fuses spatial CNN analysis with temporal bi-directional recurrent modeling for frame sequences. Preprocessing and explainable AI methods (e.g., Grad-CAM and LIME) improve detection reliability and interpretability.","Md Ashikuzzaman Esti  \nA Hybrid Approach to Machine Learning-Based Deepfake Video Detection  \nSchool of Technology and Innovations  \nMasters Thesis Computing Sciences  \n\n| UNIVERSITY OF VAASA\u003Cbr>School of Technology and Innovations\u003Cbr>Author: Md Ashikuzzaman Esti\u003Cbr>Title of the thesis: A Hybrid Approach to Machine Learning-Based Deepfake Video\u003Cbr>Detection\u003Cbr>Degree: Master of Science in Computing Sciences\u003Cbr>Major: Sustainable and Autonomous Systems\u003Cbr>Supervisor: Mohammed Elmusrati\u003Cbr>Thesis Evaluator: Petri Välisuo\u003Cbr>Year: 2025 Pages: 72 |\n| --- |\n| ABSTRACT:\u003Cbr>In modern times, people regularly share a large number of videos on the internet by posting indifferent social media or online video sharing platforms. These videos are floating around the internet and are easily accessible to the public. The emergence of generative AI technology has made the process of manipulating these videos very easy. One common method is to replace an individual's face or copy facial features and movements in a video. The entire process is done so smoothly that the final video looks almost real, even though it is fake. This type of video manipulation is known as a deepfake. Furthermore, it creates serious concerns about security, misinformation, and personal privacy, as these videos often portray individuals doing things they never did. However, these circumstances can be tackled by differentiating fake videos from real ones, creating an effective detection system. In this research, a publicly available UADFV deepfake dataset was selected. A hybrid approach incorporating machine learning and its subset technology was proposed to detect fake videos by analyzing both spatial and temporal features present in frame sequences extracted from the videos. The model was created effectively by combining multiple convolutional neural networks for spatial analysis with a bi-directional recurrent neural network understanding the temporal dependencies across video frames. This hybrid structure detects both frame-level visual inconsistencies and unnatural frame transitions that, in most cases, flag the content as deepfake. In addition to the hybrid architecture, different effective preprocessing techniques were applied to clarify the video frames and highlight subtle inconsistencies before model training. It is also worth noting that interpretability in an AI detection system is very important. Thus, the model also incorporated explainable AI methods to illustrate which area in the facial region impacts the model's final binary prediction the most. The interpretability of this model further validates its final decision. Overall, this study aims to identify deepfake videos with high accuracy using an effective hybrid modelling approach, and also involves interpretability in the model's final outcome. |\n\nKEYWORDS: (Generative AI, Deepfake, Spatial, Temporal, Explainable AI, Hybrid)  \nContents  \n1 Introduction 8  \n1.1 Research Questions 10  \n2 Literature Review 11  \n2.1 Overview of Deepfake Technology 11  \n2.2 Methods for Deepfake Generation 13  \n2.2.1 Autoencoder in Deepfake Creation 14  \n2.2.2 Generative Adversarial Networks (GANs) in Deepfake Creation 16  \n2.3 Deepfake Detection Techniques 18  \n2.3.1 Simple Machine Learning Approach 19  \n2.3.2 Single Architecture Model 23  \n2.3.3 Hybrid Architecture Model 25  \n2.4 Explainability in AI-driven Deepfake Detection Models 29  \n2.4.1 Explainable AI Techniques 30  \n3 Research Methodology 34  \n3.1 Dataset Selection 34  \n3.2 Proposed Steps for Detecting Deepfakes 35  \n3.2.1 Facial Feature Extraction 35  \n3.2.2 Temporal Feature Collection 36  \n3.2.3 Integration of Hybrid Model 37  \n3.3 Proposed Hybrid Model Architecture 38  \n3.3.1 EfficientNetV2B3 39  \n3.3.2 XceptionNet 41  \n3.3.3 VGG 16 42  \n3.3.4 Bi-Directional LSTM (Recurrent Neural Network) 43  \n3.3.5 Compete Hybrid Architecture 47  \n4 Results and Analysis 49  \n4.1 Test Accuracy and Loss 49  \n4.2 Classification Report 50  \n4.3 Training vs Validation Accuracy and","cbCailEykk52a2eu","https://ap.wps.com/l/cbCailEykk52a2eu","pdf",1694420,3,1,72,"English","en",105,"# Introduction\n## Research Questions\n# Literature Review\n## Overview of Deepfake Technology\n## Methods for Deepfake Generation\n## Deepfake Detection Techniques\n## Explainability in AI-driven Deepfake Detection Models\n# Research Methodology\n## Dataset Selection\n## Proposed Steps for Detecting Deepfakes\n## Proposed Hybrid Model Architecture\n# Results and Analysis\n## Test Accuracy and Loss\n## Classification Report\n## Explainable AI Interpretation\n# Discussion\n## Hybrid CNN-RNN Model Development for Deepfake Detection\n## Effectiveness of Dataset-Specific Preprocessing Techniques\n## Explainable AI Tools for Enhanced Interpretability\n# Conclusion\n## Summary of Research Objectives and Contributions\n## Limitations\n## Recommendation for Future Study","[{\"question\":\"Why is deepfake video detection important in this research?\",\"answer\":\"Deepfakes can be generated smoothly using generative AI, enabling realistic fake videos that lead to security threats, misinformation, and privacy violations. The thesis focuses on differentiating fake videos from real ones to mitigate these concerns.\"},{\"question\":\"What dataset and modeling strategy does the thesis use?\",\"answer\":\"The study uses the publicly available UADFV deepfake dataset and proposes a hybrid approach. It combines multiple CNNs for spatial feature analysis and a bi-directional recurrent network to capture temporal dependencies across frames.\"},{\"question\":\"How does the thesis improve interpretability of its detection results?\",\"answer\":\"The model incorporates explainable AI methods to identify which facial-region areas most influence the final binary prediction. The thesis highlights techniques such as Grad-CAM heatmaps and LIME explanations.\"}]","A Hybrid Approach to Machine Learning-Based Deepfake Video Detection - Masters Thesis | PDF",1785945529,181,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"a-hybrid-approach-to-machine-learning-based-deepfake-video-detection-masters-thesis","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/a-hybrid-approach-to-machine-learning-based-deepfake-video-detection-masters-thesis/128201/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is deepfake video detection important in this research?","Question",{"text":76,"@type":77},"Deepfakes can be generated smoothly using generative AI, enabling realistic fake videos that lead to security threats, misinformation, and privacy violations. The thesis focuses on differentiating fake videos from real ones to mitigate these concerns.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What dataset and modeling strategy does the thesis use?",{"text":81,"@type":77},"The study uses the publicly available UADFV deepfake dataset and proposes a hybrid approach. It combines multiple CNNs for spatial feature analysis and a bi-directional recurrent network to capture temporal dependencies across frames.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the thesis improve interpretability of its detection results?",{"text":85,"@type":77},"The model incorporates explainable AI methods to identify which facial-region areas most influence the final binary prediction. The thesis highlights techniques such as Grad-CAM heatmaps and LIME explanations.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]