Wednesday, September 30, 2020
Home Cybersecurity News New algorithm protects against deep fakes

New algorithm protects against deep fakes

The relative ease with which internet users can create deepfakes could further muddy the waters of what is real and fake online, particularly in arenas like politics.

A new algorithm adds a filter to videos and photos to prevent deepfakes, researchers say.

In today’s complex media environment, people can struggle to separate fact from fiction online. A relatively new phenomenon is making that struggle even harder: deepfakes.

Using deep neural networks (a machine learning technique), it’s become increasingly easy to convincingly manipulate images and videos of people by doctoring their speech, movements, and appearance.

Protecting Media

In response, researchers have created an algorithm that generates an adversarial attack against facial manipulation systems in order to corrupt and render useless attempted deepfakes.

The researchers’ algorithm allows users to protect media before uploading it to the internet by overlaying an image or video with an imperceptible filter.

When a manipulator uses a deep neural network to try to alter an image or video protected by the algorithm, the media is either left unchanged or completely distorted, the pixels rendering in such a way that the media becomes unrecognizable and unusable as a deepfake.

The researchers have made their open-source code publicly available. Their paper has not yet been peer-reviewed and is available on arXiv.

Nataniel Ruiz, a doctoral candidate in computer science at Boston University and coauthor of the paper, says that the idea for the project came to him after he got interested in the rapidly advancing techniques for creating deepfakes. He hit on the idea of disrupting deepfakes after talking with his doctoral advisor, Stan Sclaroff, dean of Boston University’s College of Arts & Sciences and professor of computer science, about the possible malicious uses of deepfake technology.

Deepfakes first rose to prominence with applications that realistically transpose an individual’s face onto another’s body, yet necessitate large amounts of images of the individual. Recent advances in the field now allow for the creation of fake images and video of people using only a few images. It has also become easier for ordinary citizens to create deepfakes.

Last year, for instance, the iPhone app FaceApp entered the zeitgeist. Created by a Russian company, the app allows everyday users to transform images of individuals into older versions of themselves, change their expression into a smile, or other tricks.

Trust Problems for Politicians

The relative ease with which internet users can create deepfakes could further muddy the waters of what is real and fake online, particularly in arenas like politics. Detecting deepfake images, audio, or video could be one approach to solving this trust problem, although it may prove to be harder than expected. Facebook is currently holding a competition, searching for a team of researchers that can effectively detect deepfakes.

Now, the researchers are pursuing even more sophisticated techniques for disrupting deepfakes.

“We covered what we call ‘white-box’ attacks in our work, where the network and its parameters are known to the disruptor,” says coauthor Sarah Adel Bargal, a research assistant professor of computer science.

“A very important next step is to develop methods for ‘black-box’ attacks that can disrupt deepfake networks [in ways] inaccessible to the disruptor… [and] we are currently working on making this a reality.”

  • Jeremy Schwab serves as the Director of Integrated Marketing & Communications for the College and Graduate School of Arts & Sciences at Boston University. This article was originally published on Futurity

 

Advertisement
Jeremy Schwab
Jeremy Schwab
Jeremy Schwab serves as the Director of Integrated Marketing & Communications for the College and Graduate School of Arts & Sciences at Boston University.

Stay Connected

Join Our Newsletter

Must Read

Tips for living online – lessons from six months of the COVID-19 pandemic

Valentine’s Day was sweet, spring break was fun, then… boom! COVID-19. Stay-at-home orders, workplace shutdowns, school closures and social distancing requirements changed lives almost...

What we learned from listening to 1.5 million robocalls on 66,000 phone lines

More than 80% of robocalls come from fake numbers – and answering these calls or not has no effect on how many more you’ll...

Deep learning AI stuns scientists with poetry and journalism

Seven years ago, my student and I at Penn State built a bot to write a Wikipedia article on Bengali Nobel laureate Rabindranath Tagore’s...

Spooky quantum breakthrough could change physics forever

MIP* = RE is not a typo. It is a groundbreaking discovery and the catchy title of a recent paper in the field of...

Related News

Tips for living online – lessons from six months of the COVID-19 pandemic

Valentine’s Day was sweet, spring break was fun, then… boom! COVID-19. Stay-at-home orders, workplace shutdowns, school closures and social distancing requirements changed lives almost...

What we learned from listening to 1.5 million robocalls on 66,000 phone lines

More than 80% of robocalls come from fake numbers – and answering these calls or not has no effect on how many more you’ll...

Deep learning AI stuns scientists with poetry and journalism

Seven years ago, my student and I at Penn State built a bot to write a Wikipedia article on Bengali Nobel laureate Rabindranath Tagore’s...

Spooky quantum breakthrough could change physics forever

MIP* = RE is not a typo. It is a groundbreaking discovery and the catchy title of a recent paper in the field of...

Our solar system’s four most promising worlds for alien life

The Earth’s biosphere contains all the known ingredients necessary for life as we know it. Broadly speaking these are: liquid water, at least one...

This site uses Akismet to reduce spam. Learn how your comment data is processed.