The Hidden Second Face of Deepfakes

A lot of times when you read about deepfakes (more professionally known as synthetic media) the common themes being explored is only one of the two faces of deepfakes the negative side, however, I want to explore some of the positive things deepfakes can be used for so you can get a full scope of the capabilities of deepfakes.

Well, what’s a deepfake anyways? Glad you asked, simple answer: artificial intelligence-generated media that has seamlessly stitch anyone in the world into a video or photo they never actually in and a summarised more technical answer: deepfakes are made by using a GAN (generative adversarial network) a type of deep learning artificial intelligence. It uses two neural networks that rival each other to generate a synthetic version of data that can pass for real data, one of the neural networks is called the generator (generates new data instances) and the other is called a discriminator (evaluates them for authenticity). The purpose of the generator is to generate synthetic media that is given to the discriminator, which its purpose is to identify whether the media is fake or real, they are trained together until it achieves acceptable accuracy (discriminator fooled 50% of the time). A great more visual and detailed explanation of GANs can be found in the video below:

So now that we have a better understanding of how deepfakes are created we can begin to explore the positive uses of deepfakes. In 2019, for a UK-based charity called Malaria Must Die, the company Synthesia used deepfake voice technology in a video in which David Beckham appealed to the end to malaria in nine different languages with pretty convincing lip-sync. Synthesia also proved helpful during the pandemic as it helped advertising company WPP to create training videos without the fear of spreading the disease.

A pretty incredible use of deepfakes within the medical field is the research by Mayo Clinic and the MGH & BWH Center for Clinical Data Science that used deepfake technology to create “fake” brain scans based on actual patient data. These fake scans are then used to train algorithms to spot tumours in real images.

Another positive use of deepfakes is in law enforcement to protect real victims of child sex abuse while catching sexual predators. Earlier this year Germany passed legislation allowing the use of deepfakes to rid the world of online predators. However, there is a real conversation to be had about the ethics of the use of the technology in this regard.

On a lighter note, cool uses of deepfakes would be personal avatars that can allow people to try different clothes and hairstyles without fully committing, just imagine you don’t know whether the fringe you have always wanted will look good on you could use the technology to help your decision.

Although these are some incredible uses of deepfakes there is no denying the dark cloud that will always loom over deepfakes, with stories coming out every week about the dangerous uses of deepfakes. With proper and heavily enforced regulations, the technology could truly benefit society.

Thumbnail Credit: https://www.arm.com/blogs/blueprint/arm-ai-trust-manifesto