Friday, 30 October 2020 09:14

Monash/IIT AI identifies 91% of deepfakes


Machine learning made deepfakes possible, and is also being used to detect them. Researchers at Monash University and the Indian Institute of Technology Ropar have developed an approach they say outperforms other ML models.

The new algorithm works by generating a "dissonance score" by detecting discrepancies between the audio and video content. Examples include unnatural face or lip movements, or audio lags.

"The machine learning method we've developed is applying a detection technique similar to watching a foreign film with overlaid audio that is not in sync with the lip movements. This disharmony between the audio and the visual leads the viewer to notice that the video isn't quite right, which is what we're mimicking with the machine learning algorithm," said project lead Abhinav Dhall from Monash University's faculty of information technology.

"By producing a 'dissonance score', the algorithm detects if something isn't quite right in a video and then identifies the exact part of a video that has been manipulated. The machine learning algorithm independently learns from these discriminative features, further advancing its ability to detect future deepfakes."

The approach has been tested on more than 18,000 deepfakes. The success rate for distinguishing between genuine and manipulated videos is 91.5%, which the researchers say is better than other advanced deepfake detection methods.

"Deepfakes are becoming an increasingly major concern worldwide. They build upon the problems created by fake news and pose a huge potential threat to democracy. With the upcoming US election, AI-generated images, audio and video are increasingly affecting our ability to separate fact from fiction in the political sphere. A reliable deepfake detection algorithm is needed now more than ever," said Indian Institute of Technology Ropar associate professor Ramanathan Subramanian.

Subscribe to ITWIRE UPDATE Newsletter here


The much awaited iTWire Shop is now open to our readers.

Visit the iTWire Shop, a leading destination for stylish accessories, gear & gadgets, lifestyle products and everyday portable office essentials, drones, zoom lenses for smartphones, software and online training.

PLUS Big Brands include: Apple, Lenovo, LG, Samsung, Sennheiser and many more.

Products available for any country.

We hope you enjoy and find value in the much anticipated iTWire Shop.



iTWire TV offers a unique value to the Tech Sector by providing a range of video interviews, news, views and reviews, and also provides the opportunity for vendors to promote your company and your marketing messages.

We work with you to develop the message and conduct the interview or product review in a safe and collaborative way. Unlike other Tech YouTube channels, we create a story around your message and post that on the homepage of ITWire, linking to your message.

In addition, your interview post message can be displayed in up to 7 different post displays on our the site to drive traffic and readers to your video content and downloads. This can be a significant Lead Generation opportunity for your business.

We also provide 3 videos in one recording/sitting if you require so that you have a series of videos to promote to your customers. Your sales team can add your emails to sales collateral and to the footer of their sales and marketing emails.

See the latest in Tech News, Views, Interviews, Reviews, Product Promos and Events. Plus funny videos from our readers and customers.


Stephen Withers

Stephen Withers is one of Australia¹s most experienced IT journalists, having begun his career in the days of 8-bit 'microcomputers'. He covers the gamut from gadgets to enterprise systems. In previous lives he has been an academic, a systems programmer, an IT support manager, and an online services manager. Stephen holds an honours degree in Management Sciences and a PhD in Industrial and Business Studies.

Share News tips for the iTWire Journalists? Your tip will be anonymous




Guest Opinion

Guest Interviews

Guest Reviews

Guest Research

Guest Research & Case Studies

Channel News