Deepfake Detection Analyzing Hybrid Dataset Utilizing CNN and SVM

Abstract

<p>Social media is currently being used by many individuals online as a major source of information. However, not all information shared online is true, even photos and videos can be doctored. Deepfakes have recently risen with the rise of technological advancement and have allowed nefarious online users to replace one’s face with a computer-generated face of anyone they would like, including important political and cultural figures. Deepfakes are now a tool to be able to spread mass misinformation. There is now an immense need to create models that are able to detect deepfakes and keep them from being spread as seemingly real images or videos. In this paper, we propose a new deepfake detection schema using two popular machine learning algorithms; support vector machine and convolutional neural network, along with a publicly available dataset named the 140k Real and Fake Faces to accurately detect deepfakes in images with accuracy rates reaching as high as 88.33%. </p>

The current landscape of digital forensics employing machine learning approaches: A Review

“…To summaries, the SVM method is a potent tool in machine learning, applicable in several domains, particularly when classifying sophisticated and multidimensional data is required. In [52] the authors the authors build ML framework employing SVM and Convolutional Neural Networks (CNN) in deepfake detection using 140k real and fake faces collected from Kaggle. The classification accuracies obtained were 81.69% with SVM and 88.33% with CNN.…”

“…Investigate Video Forensic KNN, SVM Building a ML approach for investigating crime scenes in mobile phones. [52] 2023 Analysis Image Forensic SVM, CNN Developing a specialized deepfake detection algorithm that specifically targets the identification of deepfakes in images. [53] 2023 Database Forensic SVM memory snapshot prediction framework using trained ML method [54] 2022 Analysis Video Forensic SVM, CNN Confirm that the efficacy of handcrafted features may decrease to some extent due to differences between the training and test datasets.…”

“…[49] KNN high-dimensional data KNN algorithm is inefficient in dealing with large-dimensional data, such as forensic data, which is sometimes characterized by a large number of features. [52] SVM Imbalanced Datasets SVM has difficulties dealing with the imbalanced data set that occasionally characterizes digital forensic data. [58] PCA Assumption of Linearity…”