Skip to main content
5 votes

Is it possible to detect image manipulation, for example deep fakes?

This is what the discriminator in a GAN does. The generator produces synthetic images. The discriminator tries to tell the real from the synthetic images. Eventually, perhaps, the generator gets so ...
Dave's user avatar
  • 628
5 votes
Accepted

Isn't deep fake detection bound to fail?

Not necessarily it depends on the function of the problem space for both the GANs. A real world example: a batter's reaction time and a pitchers max speed are actual bounded values based on genetics ...
Michael Hearn's user avatar
3 votes

What are some tactics for recognizing artificially made media?

Digital Media Forensics (DMF) field aims to develop technologies for the automated assessment of the integrity of an image or video, so DMF is the field you are looking for. There are several ...
nbro's user avatar
  • 40.9k
3 votes
Accepted

Why don't those developing AI Deepfake detectors use two detectors at once so as to catch deepfakes in one or the other?

Because it is possible to fool many different models at once. See table 2 in this paper, for an example using adversarial perturbations: https://arxiv.org/pdf/1610.08401.pdf That being said, there is ...
Sunny88's user avatar
  • 196
3 votes
Accepted

Can GANs be used to generate something other than images?

They can indeed. Although generally they are kept to images because at the moment, they are the best at that, but not the best in other areas that you might consider. GANs can be used for audio ...
Recessive's user avatar
  • 1,396
2 votes
Accepted

How do deepfakes work and how they might be dangerous?

In general, deepfakes rely on advanced context-aware digital signal manipulations - usually image, video or audio - that allow for very natural looking modifications of content that previously have ...
Neil Slater's user avatar
  • 32.7k
2 votes

How to make deepfake video without a fancy PC?

Yes. There are services that provide free environment to run jupyter notebooks for research purposes (with GPU included, which is crucial for neural networks) - such as Google Colaboratory and Kaggle ...
zeyger's user avatar
  • 121
2 votes

Can we combat against deepfakes?

I think this game will go pretty crazy, because, at some point, the generator AI will be able to generate absolutely perfect images. Actually, no, just perfect enough that no AI can be sure whether ...
Kenivia's user avatar
  • 149
1 vote

Can we combat against deepfakes?

As mshlis begins to touch on, yes we can. However, it will be an unending war. There are quite a few reasons for this. For one, the problem itself is not simple. There are many different 'versions' of ...
hisairnessag3's user avatar
1 vote

How to make deepfake video without a fancy PC?

Take a look at using AWS You can spin up an instance with as much processing power as you need and by using their pre-built images it will already be preconfigured with a lot of the packages etc you ...
Aphire's user avatar
  • 111
1 vote

Is it possible to spot photoshoped or edited photos using AI?

It is possible! Here is an article by Adobe where they explain how they do it: https://theblog.adobe.com/spotting-image-manipulation-ai/ The algorithm for this would almost certainly be a ...
axon's user avatar
  • 53
1 vote

What are some tactics for recognizing artificially made media?

I think context is important here. Using tactics like those used by Scotland Yard for over a century is probably the best way. Establishing alibis, realistic time lines, motives. For a legal setting, ...
N E Techno Tech Blog's user avatar
1 vote

What are some tactics for recognizing artificially made media?

The techniques you mention use GANs. The key idea of GANs is that you have a generator and a discriminator. The generator generates new content, the discriminator has to tell if the content is from ...
Martin Thoma's user avatar
  • 1,055

Only top scored, non community-wiki answers of a minimum length are eligible