Deepfakes: Trick or treat?

@article{Kietzmann2020DeepfakesTO,
  title={Deepfakes: Trick or treat?},
  author={Jan H. Kietzmann and Linda W. Lee and Ian Paul McCarthy and T. Kietzmann},
  journal={Business Horizons},
  year={2020},
  volume={63},
  pages={135-146}
}

Image and video manipulation: The generation of deepfakes

The growth of fake news is nowadays a growing reality, leading to users feeling insecure when consuming information. Text-based news is perhaps the most manipulated, but the video is rapidly gaining

Deepfake videos: synthesis and detection techniques - a survey

The study aims to present an all-inclusive overview of deepfakes by providing insights into the deepfake creation techniques and the latest detection methods, facilitating the development of a robust and effective deepfake detection solution.

Deepfake false memories

Though participants rated the deepfake videos as convincing, dangerous, and unethical, and some participants did report false memories after viewing deepfakes, the deep fake video format did not consistently increase false memory rates relative to the text-only or text-with-photograph conditions.

Seeing is Believing: Exploring Perceptual Differences in DeepFake Videos

An investigative user study is performed and existing AI detection algorithms from the literature are analyzed to demystify the unknowns that are at play behind the scenes when detecting DeepFakes.

“All Around Me Are Synthetic Faces”: The Mad World of AI-Generated Media

This article explains what deepfakes and GANs are, how they work and discusses the threats and opportunities resulting from these forms of synthetic media.

Deepfakes: A Digital Transformation Leads to Misinformation

A portmanteau combines deep learning aspects of AI with the doctored or falsified enhancements that deem the content fake and now deepfake or misinformation results.

Artificial Intelligence in Digital Media: The Era of Deepfakes

  • S. Karnouskos
  • Computer Science
    IEEE Transactions on Technology and Society
  • 2020
This article investigates the deepfakes via multiangled perspectives that include media and society, media production, media representations, media audiences, gender, law, and regulation, as well as politics, which indicate that as a society, the authors are not ready to deal with the emergence ofdeepfakes at any level.

DeepFake Detection using 3D-Xception Net with Discrete Fourier Transformation

This work has proposed a new method for detecting deep fake videos using 3D Inflated Xception Net with Discrete Fourier Transformation, which is the first attempt to use a 3D Xception net for categorizing video-based data.

Edited Media Understanding Frames: Reasoning About the Intent and Implications of Visual Misinformation

Examining Edited Media Frames, a new formalism to understand visual media manipulation as structured annotations with respect to the intents, emotional reactions, attacks on individuals, and the overall implications of disinformation, yields promising results.
...

References

SHOWING 1-10 OF 25 REFERENCES

Text-based editing of talking-head video

This work proposes a novel method to edit talking-head video based on its transcript to produce a realistic output video in which the dialogue of the speaker has been modified, while maintaining a seamless audio-visual flow (i.e. no jump cuts).

Synthesizing Obama

Given audio of President Barack Obama, a high quality video of him speaking with accurate lip sync is synthesized, composited into a target video clip, and a recurrent neural network learns the mapping from raw audio features to mouth shapes to produce photorealistic results.

In the Eyes of the Law: Perception Versus Reality in Appraisals of Video Evidence

Video evidence has been widely welcomed into courtrooms, largely on the implicit faith that video objectively represents the legally relevant facts as they are. In this paper, we argue that both lay

Deep Neural Networks in Computational Neuroscience

Deep neural networks represent a powerful framework for building task-performing models and will drive substantial insights in computational neuroscience.

Overt Visual Attention as a Causal Factor of Perceptual Awareness

It is demonstrated that distinct patterns of overt attentional selection precede object awareness and thereby directly builds on recent electrophysiological findings suggesting two distinct neuronal mechanisms underlying the two phenomena.

Policing Made Visible: Mobile Technologies and the Importance of Point of View

Cameras are ubiquitous and increasingly mobile. While CCTV has captured considerable attention by surveillance researchers, the new visibility of police activities is increasingly produced by

Photographic truth and evidence

The application of visual material is becoming increasingly more prominent when presenting forensic evidence in contemporary courts. This paper examines how photographic evidence is used as a means

Unpacking the Social Media Phenomenon: Towards a Research Agenda

In this paper, we highlight some of the challenges and opportunities that social media presents to researchers, and offer relevant theoretical avenues to be explored. To do this, we present a model