Ride the Lightning

Can Mice Save Us From Deepfakes? Don’t Laugh, They Might!

August 15, 2019

When I read three very similar stories that say the same thing, I take notice. So my sources are a post from Naked Security, a post from BBC News, and a post from CNET.

As part of the evolving battle against deepfakes – videos and audio mostly featuring famous people, created using machine learning, designed to appear genuine – researchers are turning to new methods to defeat the increasingly sophisticated technology.

At the University of Oregon's Institute of Neuroscience, one of the more outlandish ideas is being tested. A research team is working on training mice to understand irregularities within speech, a task the animals can do with remarkable accuracy.

The research could be used to help sites such as Facebook and YouTube detect deepfakes before they are able to spread online – and no, the companies won't need their own mice.

"While I think the idea of a room full of mice in real time detecting fake audio on YouTube is really adorable," says Jonathan Saunders, one of the project's researchers, "I don't think that is practical for obvious reasons. The goal is to take the lessons we learn from the way that they do it, and then implement that in the computer."

Mr Saunders and team trained their mice to understand a small set of phonemes, the sounds we make that distinguish one word from another. "We've taught mice to tell us the difference between a 'buh' and a 'guh' sound across a bunch of different contexts, surrounded by different vowels, so they know 'boe' and 'bih' and 'bah' – all these different fancy things that we take for granted. And because they can learn this really complex problem of categorizing different speech sounds, we think that it should be possible to train the mice to detect fake and real speech."

The mice were given a reward each time they correctly identified speech sounds, which was up to 80% of the time. That's not perfect, but coupled with existing methods of detecting deepfakes, it could be extremely valuable input.

According to researchers, who presented their findings during a presentation at the Black Hat security conference last week, recent work has shown that "the auditory system of mice resembles closely that of humans in the ability to recognize many complex sound groups."

As they said, "mice do not understand the words but respond to the stimulus of sounds and can be trained to recognize real vs. fake phonetic construction. We theorize that this may be advantageous in detecting the subtle signals of improper audio manipulation, without being swayed by the semantic content of the speech."

The mice are small but mighty if they can help us defeat deepfakes!

Sharon D. Nelson, Esq., President, Sensei Enterprises, Inc.
3975 University Drive, Suite 225|Fairfax, VA 22030
Email: Phone: 703-359-0700
Digital Forensics/Cybersecurity/Information Technology
https://senseient.com
https://twitter.com/sharonnelsonesq
https://www.linkedin.com/in/sharondnelson
https://amazon.com/author/sharonnelson