Deepfake Detection Using the Rate of Change between Frames Based on Computer Vision

Abstract

Recently, artificial intelligence has been successfully used in fields, such as computer vision, voice, and big data analysis. However, various problems, such as security, privacy, and ethics, also occur owing to the development of artificial intelligence. One such problem are deepfakes. Deepfake is a compound word for deep learning and fake. It refers to a fake video created using artificial intelligence technology or the production process itself. Deepfakes can be exploited for political abuse, pornography, and fake information. This paper proposes a method to determine integrity by analyzing the computer vision features of digital content. The proposed method extracts the rate of change in the computer vision features of adjacent frames and then checks whether the video is manipulated. The test demonstrated the highest detection rate of 97% compared to the existing method or machine learning method. It also maintained the highest detection rate of 96%, even for the test that manipulates the matrix of the image to avoid the convolutional neural network detection method.

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management

“…where m 2 (), m 3 () and m 4 () are 3×3, 5×5 and 7×7 convolutions, respectively. Third, it concatenates all inputs b i , i ∈ [1,4] and uses a 1×1 convolution to fuse all features from different scales. Finally, it employs attention mechanism to adaptively allocate weights to multi-scale features.…”

“…The past decades have witnessed a booming of urban populations with ever-increased municipal facilities to serve all citizens. An effective solution to manage these facilities is smart city with Internet of Things (IoT), which is mostly benefitted from the recent development of Artificial Intelligence (AI) [1][2][3]. To support the smart city, an economic but efficient electric power management system is indispensable [4].…”

Survey: Analysis and Detection of Deepfake in Multimedia Through Advanced Deep Learning Approaches

“…In a work by Gihun Lee and Mihui Kim, et al [6], an innovative approach to identify deepfake videos is introduced, leveraging the rate of change in computer vision features between frames. The method employs a Deep Neural Network (DNN) based on the variance across a specified number of frames, marking a departure from conventional detection of DeepFake methods by avoiding the utilization of a CNN to mitigate detection evasion through metric alterations.…”

Deep Fake Detection Using Computer Vision-Based Deep Neural Network with Pairwise Learning

“…Figure 1: Real and deepfake image [1] movies and television clips. For those reasons, truth-finding in the digital domain is critical and challenging.…”

“…It is created to manipulate the activity of the targeted person by saying the messages. Due to the development of smartphones and social media, deepfake technology poses a threat to digital content and spreads false information that is not identified by human eyes [1]. Fig.…”