• Corpus ID: 197547831

Deepfakes : How a pervert shook the world

  title={Deepfakes : How a pervert shook the world},
  author={Ronit Chawla},
  journal={International Journal for Advance Research and Development},
  • R. Chawla
  • Published 22 June 2019
  • Art
  • International Journal for Advance Research and Development
Recently a software has made it easy to create hyper-realistic face swaps in videos that leaves little-to-no traces of manipulation, in what is known as “deepfake” videos. Scenarios, where these AI manipulated/generated videos, are used for political distress, blackmail or even terrorism are easily envisioned as a near dystopia. This paper explores the various aspects of deepfake videos including its consequences and newly developed innovations in detecting deepfakes. 

What's wrong with this video? Comparing Explainers for Deepfake Detection

This work develops, extend and compare white-box, black-box and model-specific techniques for explaining the labelling of real and fake videos, and adapt SHAP, GradCAM and self-attention models to the task of explaining the predictions of state-of-the-art detectors based on EfficientNet, trained on the Deepfake Detection Challenge (DFDC) dataset.

A Review of Image Processing Techniques for Deepfakes

This study aims to highlight the recent research in deepfake images and video detection, such as deepfake creation, various detection algorithms on self-made datasets, and existing benchmark datasets, as well as how to counter the threats from deepfake technology and alleviate its impact.

Deepfake Detection on Videos Based on Ratio Images

Inspired by the concept of ratio images, this method extracts features based on the ratio between adjacent frames for the face and its background from a different perspective: extracting features that can account for inter-frame changes on a video.

The Deepfake Challenges and Deepfake Video Detection

This paper aims to investigate deepfake challenges, and to detect deepfake videos by using eye blinking, using convolutional neural networks to classify the eye states and long short term memory for sequence learning and the eye aspect ratio was used to calculate the height and width of open and closed eyes and to detects the blinking intervals.

The Distinct Wrong of Deepfakes

Deepfake technology presents significant ethical challenges. The ability to produce realistic looking and sounding video or audio files of people doing or saying things they did not do or say brings


The present research examines its origin and history while assessing how deepfake videos and photos are created, and focuses on the impact deepfake has made on society in terms of how it has been applied.

Do Deepfakes Adequately Display Emotions? A Study on Deepfake Facial Emotion Expression

Results show that emotional expressions are not adequately transferred between original recordings and the deepfakes created from them, which indicates that performer emotion expressiveness should be considered for better deepfake generation or detection.

The Emergence of Deepfake Technology: A Review

In recent years, fake news has become an issue that is a threat to public discourse, human society, and democracy (Borges et al., 2018; Qayyum et al., 2019). Fake news refers to fictitious news style

The Forgery of Deepfake and the “Advent” of Artificial Intelligence

The concept of politics changes its semantic value according to the historical period and the cultural changes affecting the social fabric. In classical literature, there was no distinction between

Deepfakes and Domestic Violence: Perpetrating Intimate Partner Abuse Using Video Technology

ABSTRACT Technology-facilitated abuse is becoming an increasingly standard component of domestic violence, having proliferated in recent decades due to an increased use of smart phones and the



Recent Progress of Face Image Synthesis

A comprehensive review of typical face synthesis works that involve traditional methods as well as advanced deep learning approaches is provided, particularly, Generative Adversarial Net (GAN) is highlighted to generate photo-realistic and identity preserving results.

Graph Regularized Auto-Encoders for Image Representation.

  • Yiyi LiaoYue WangYong Liu
  • Computer Science
    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • 2017
Inspired by the recent successes of deep architectures, this work proposes a local invariant deep nonlinear mapping algorithm, called graph regularized auto-encoder (GAE), which preserves the local connectivity from the original image space to the representation space, while the stackedAuto-encoders provide explicit encoding model for fast inference and powerful expressive capacity for complex modeling.

People Are Using Face-Swapping Tech to Add Nicolas Cage to Random Movies and What Is 2018

  • 2018

You thought fake news was bad? Deep fakes are where the truth goes to die

  • 2018