An evolutionary- convolutional neural network for fake image detection (original) (raw)

Real-Time Advanced Computational Intelligence for Deep Fake Video Detection

Applied Sciences

As digitization is increasing, threats to our data are also increasing at a faster pace. Generating fake videos does not require any particular type of knowledge, hardware, memory, or any computational device; however, its detection is challenging. Several methods in the past have solved the issue, but computation costs are still high and a highly efficient model has yet to be developed. Therefore, we proposed a new model architecture known as DFN (Deep Fake Network), which has the basic blocks of mobNet, a linear stack of separable convolution, max-pooling layers with Swish as an activation function, and XGBoost as a classifier to detect deepfake videos. The proposed model is more accurate compared to Xception, Efficient Net, and other state-of-the-art models. The DFN performance was tested on a DFDC (Deep Fake Detection Challenge) dataset. The proposed method achieved an accuracy of 93.28% and a precision of 91.03% with this dataset. In addition, training and validation loss was 0...

Fake Image Detection Using Deep Learning

Informatica

With the emergence of numerous electronic communication programs and image processing programs, as well as an increase in the number of people who use them with a zeal for publishing everything related to their lives and their special pictures and their fear of those who might use these pictures for malicious or humorous purposes, it has become necessary to have specialized and precise systems to determine whether a picture is real or fake. Our work aims to detect real and fake faces by using and modifying one of the most efficient CNN architectures, EfficientNetB0, after improving the architecture with additional fully connected layers and efficiently training the model by using the Adam optimizer and a scheduler learning rate technique. Our findings on the well-known 140k-real-and-fake-faces Kaggle dataset showed state-of-the-art accuracy with the lowest error rate. We achieved 99.06% accuracy, and 0.0569 error rate respectively. Povzetek: Predstavljena je metoda globokih mrež, ki z uporabo EfficientNetB0 in optimizatorja Adam na Kagglovih 140.000 obrrazih ločuje prave in lažne obraze z 99,06% točnostjo.

Deepfake Video Detection Using Convolutional Neural Network

With the advent of new technological enhancements in artificial intelligence, new sophisticated AI techniques are used to create fake videos. Such videos can pose a great threat to the society in various social and political ways and can be used for malicious purposes. These fake videos are called deepfakes. Deepfakes refer to manipulated videos, or other digital representations produced by sophisticated artificial intelligence, that yield fabricated images and sounds that appear to be real. A deep-learning system can produce a persuasive counterfeit by studying photographs and videos of a target person from multiple angles, and then mimicking its behaviour and speech patterns. Detecting these videos is a massive problem because of the increasing developments in more realistic deepfake creation technologies emerging every now and then. The paper aims to solve this problem by proposing a model that analyses the frames of the videos using deep learning approach to detect inconsistencies in facial features, compression rate and discrepancies introduced in the videos while creating them. The model uses a convolutional neural network along with transfer learning to train the model that can catch these instilled errors in the deepfakes. The neural network is trained on these discrepancies induced during deepfake creation around the face. It uses a dataset called "Celeb-DF: A New Dataset for DeepFake Forensics" to train the model. The paper further discusses methods that can be used, in detail, to improve learning by this model.

IJERT-Deep Fake Detection using Neural Networks

International Journal of Engineering Research and Technology (IJERT), 2021

https://www.ijert.org/deep-fake-detection-using-neural-networks https://www.ijert.org/research/deep-fake-detection-using-neural-networks-IJERTCONV9IS03075.pdf Deepfake is a technique for human image synthesis based on artificial intelligence. Deepfake is used to merge and superimpose existing images and videos onto source images or videos using machine learning techniques. They are realistic looking fake videos that cannot be distinguished by naked eyes. They can be used to spread hate speeches, create political distress, blackmail someone, etc. Currently, Cryptographic signing of videos from its source is done to check the authenticity of videos. Hashing of a video file into "fingerprints" (small string of text) is done and reconfirmed with the sample video and thus verified whether the video is the one originally recorded or not. However, the problem with this technique is that the fingerprints and hashing algorithms are not available with common people. In this paper the proposed system follows a detection approach of Deepfake videos using Neural Networks. Binary classification of deepfakes was done using combination of Dense and Convolutional neural network layers. It was observed that 91% accuracy was obtained in Adam and 88% was obtained in sgd(stochastic gradient descent) for categorial cross entropy. In binary cross entropy, 90% accuracy was seen in Adam and 86% accuracy was noticed in sgd whereas, 86% accuracy in Adam and 80% accuracy in sgd was obtained in mean square.

Analysis of the current state of deepfake techniques-creation and detection methods

Deep learning has effectively solved complicated challenges ranging from large data analytics to human level control and computer vision. However, deep learning has been used to produce software that threatens privacy, democracy, and national security. Deepfake is one of these new applications backed by deep learning. Fake images and movies created by Deepfake algorithms might be difficult for people to tell apart from real ones. This necessitates the development of tools that can automatically detect and evaluate the quality of digital visual media. This paper provides an overview of the algorithms and datasets used to build deepfakes, as well as the approaches presented to detect deepfakes to date. By reviewing the background of deepfakes methods, this paper provides a complete overview of deepfake approaches and promotes the creation of new and more robust strategies to deal with the increasingly complex deepfakes.

Cross-Forgery Analysis of Vision Transformers and CNNs for Deepfake Image Detection

Proceedings of the 1st International Workshop on Multimedia AI against Disinformation

Deepfake Generation Techniques are evolving at a rapid pace, making it possible to create realistic manipulated images and videos and endangering the serenity of modern society. The continual emergence of new and varied techniques brings with it a further problem to be faced, namely the ability of deepfake detection models to update themselves promptly in order to be able to identify manipulations carried out using even the most recent methods. This is an extremely complex problem to solve, as training a model requires large amounts of data, which are difficult to obtain if the deepfake generation method is too recent. Moreover, continuously retraining a network would be unfeasible. In this paper, we ask ourselves if, among the various deep learning techniques, there is one that is able to generalise the concept of deepfake to such an extent that it does not remain tied to one or more specific deepfake generation methods used in the training set. We compared a Vision Transformer with an EfficientNetV2 on a cross-forgery context based on the ForgeryNet dataset. From our experiments, It emerges that EfficientNetV2 has a greater tendency to specialize often obtaining better results on training methods while Vision Transformers exhibit a superior generalization ability that makes them more competent even on images generated with new methodologies. CCS CONCEPTS • Applied computing → Computer forensics; • Computing methodologies → Computer vision.

DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learning

Advanced Sciences and Technologies for Security Applications, 2021

The rapid advancement in deep learning makes the differentiation of authentic and manipulated facial images and video clips unprecedentedly harder. The underlying technology of manipulating facial appearances through deep generative approaches, enunciated as Deep-Fake that have emerged recently by promoting a vast number of malicious face manipulation applications. Subsequently, the need of other sort of techniques that can assess the integrity of digital visual content is indisputable to reduce the impact of the creations of DeepFake. A large body of research that are performed on DeepFake creation and detection create a scope of pushing each other beyond the current status. This study presents challenges, research trends, and directions related to DeepFake creation and detection techniques by reviewing the notable research in the DeepFake domain to facilitate the development of more robust approaches that could deal with the more advance DeepFake in future.

Deep fake : An Understanding of Fake Images and Videos

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2021

The Deepfake algorithm allows its user to create fake images, audios, videos that gives very real impression but is fake in real sense. This degree of technology is achieved due to advancements in Deep Learning, Machine Learning, Artificial Intelligence and Neural Networking that is a combination of algorithms like generative adversarial network (GAN), autoencoders etc. Any technology has its positive and negative repercussions. Deep fake can come in use for helping people who have lost their speech to give them new improved voice, commercially deepfake can be used in improving animation or movie quality putting in creative imagination to work as well is therapeutic to people who have lost their dear once. Negative aspects of deep fake include creating fake images, videos, audios that look very real can cause threats to an individual’s privacy, organizations, democracy, and even national security. This review paper presents history on how deep fake emerged, will comprehend on how it works including various algorithms, major research works done on understanding deep fakes in the literature and most importantly discuss recent advancements in detection of deep fake methods and its robust preventive measures.

Using Deep Learning to Recognize Fake Faces

International journal of advanced computer science and applications/International journal of advanced computer science & applications, 2024

In recent times, many fake faces have been created using deep learning and machine learning. Most fake faces made with deep learning are referred to as "deepfake photos." Our study's primary goal is to propose a useful framework for recognizing deep-fake photos using deep learning and transformative learning techniques. This paper proposed convolutional neural network (CNN) models based on deep transfer learning methodologies in which the designed classifier using global average pooling (GAP), dropout, and a dense layer with two neurons that use SoftMax are substituted for the final fully connected layer in the pretrained models. DenseNet201, the suggested framework, produced the best accuracy of 86.85% for both the deepfake and real picture datasets, while MobileNet produced a lower accuracy of 82.78%. The obtained experimental results showed that the proposed method outperformed other stateof-the-art fake picture discriminators in terms of performance. The proposed architecture helps cybersecurity specialists fight deepfake-related cybercrimes.

An Analytical Perspective on Various Deep Learning Techniques forDeep Fake Detection

International journal of innovations in engineering and science, 2022

The advent of deep fake technology has become a crucial concern in this digital world. A serious threat to an individual's privacy, democracy, and national security can be caused by deep fake. Deep fake algorithms can develop forgery multimedia content that we cannot distinguish from genuine ones. In this era of the cyber age, it has become seemingly difficult to identify between real digital content and fake content which are published across the Internet. It is a widely used technology used by cybercriminals to deceive security systems. If we are not cautious, deep fake technology can bring about a serious threat to the future of identity verification. There are many open-source and free software available to create deep fake content which makes it easy for amateurs to create technically brilliant digital content which is fake. On the other hand, many structured and efficient technologies have been developed to identify deep fakes. A few of the techniques available are like comparing the background, analyzing the pattern in the image, considering the blinking of the Eye, considering facial attributes, considering the head position, etc. This paper gives an introduction to deep fake, and a brief on deep fake creation and detection techniques..