Top Research Papers on Deepfake Detection

A new deep learning-based method that can effectively distinguish AI-generated fake videos from real videos is described, capable of automatically detecting the replacement and reenactment deep fakes.

The rapid advancements in artificial intelligence (AI), machine learning, and deep learning have led to the development of new tools capable of manipulating multimedia content, which has been used to spread misinformation, fuel political tensions, and engage in malicious acts such as harassment and blackmail.

-The expeditious progress in facial image generation and exploitation has now come to a point where it raises serious concerns to the social and political society. This leads to the creation of fake information and new which ultimately results in loss of trust in digital content. We have developed a detection model using convolution neural network (CNN) for face detection and Recurrent neural network (RNN) for video classification. Even though this technology is remarkable it leads to social and political concerns. So far, with the help of released tools for the generation of deep fake videos ...

This paper proposes a holistic strategy employing Facenet_pytorch, MTCNN, and InceptionResnetV1 for robust deepfake detection, achieving significant strides in differentiating manipulated content from authentic media, contributing to the ethical deployment of deepfake detection technologies.

This research proposes a robust deep learning-based technique for detecting deep fakes in videos, designed to automatically identify several forms of deep forgery, including replacement and re-enactment techniques.

This study proposes a novel deepfake detection system that integrates a hybrid Recurrent Neural Network, Convolutional Neural Network, and Long Short-Term Memory architecture, employing a multi-faceted approach to training by utilizing several diverse datasets encompassing real and synthetic videos.

This study conducts a comparative analysis of three varied convolutional neural networks (CNNs) for deepfake image detection by comparing three major CNN architectures and highlights the strengths and weaknesses of each CNN architecture.

This paper proposes a binary classifier based on a 2-phase learning architecture for detecting DeepFake images and demonstrates 91% validation accuracy on a large, diverse dataset of sophisticated GAN-generated DeepFake images.

ABSTRACT Deepfake detection systems have become critical in combating the growing misuse of synthetic media, which leverages advanced AI techniques to manipulate video, audio, and images. These systems aim to identify and differentiate genuine content from altered or artificially generated media by employing various machine learning and deep learning algorithms. Key approaches include analyzing inconsistencies in visual artifacts, facial movements, audio patterns, and spatiotemporal features that are often overlooked by human perception. As deepfake technology becomes increasingly sophist...

This is the first time to employ automated machine learning to adaptively search a neural architecture for deepfake detection, and based on the explored search space, this method achieves competitive prediction accuracy compared to previous methods.

EfficientNet-B5 is used to pluck out the spatial options of those faces they are fed as a batch of input series into a two-way long- and short-term memory (BiLSTM) to extract temporal characteristics.

No single method can reliably detect all Deepfakes and, therefore, combining multiple methods is often necessary to achieve high detection rates, and it is suggested that more extensive and diverse datasets are needed to improve the accuracy of detection algorithms.

The goal of the research is to create a deep learning-based method for identifying deepfake videos that can differentiate between real and fake information by using deep learning techniques and a variety of datasets for training, which helps combat the proliferation of false visual media.

This groundbreaking research not only establishes a new benchmark in the arena of deepfake detection but also has significant ramifications for the wider field of cybersecurity and the preservation of digital authenticity.

Analytic thinking and political interest were positively associated with identifying deepfakes and negatively associated with the perceived accuracy of a fake news piece about a leaked video (whether or not the deepfake video itself was presented).

This paper presents a deep learning based approach for detecting deepfake images and videos that uses a deep convolutional neural network architecture that involves depth-wise separable convolutions to classify whether an image or video is real or fake.

The Two-Stream models, which concurrently process spatial and temporal features, demonstrate superior performance in identifying deepfake videos, thereby underscoring the significance of temporal dynamics in deepfake detection technology.

A simple and efficient pipeline for detecting fake environmental sounds based on the CLAP audio embedding is proposed and it is shown that using an audio embedding trained specifically on environmental audio is beneficial over a standard VGGish one as it provides a 10% increase in detection performance.

A pipeline with two distinct pathways for examining individual frames and video clips for detecting deepfake videos is proposed and improvements over baseline classification models for both Eff-YNet and the combined pathway are shown.

An overview of parameters that can tell us about the authenticity of videos is presented, to develop a solution or methodology that can decide whether the face in the video was replace using DeepFake technology or not with some probability.