Saturday, September 19, 2020
Home Lead Story Deepfake Detection Challenge: Facebook AI Model Detects 65% Deepfake Videos

Deepfake Detection Challenge: Facebook AI Model Detects 65% Deepfake Videos

Facebook AI model has achieved 65% accuracy to detect deepfake videos

Alarmed at the growing forged or deepfake videos on its platform, Facebook organised a Deepfake Detection Challenge and the results were not very encouraging, as the highest-performing model achieved an average precision of 65.18 per cent against real world examples as per tech news.

This, however, establishes a new shared baseline as the artificial intelligence (AI) community continues to work on this difficult and important task, said Facebook.

The Deepfake Detection Challenge drew more than 2,000 participants, who trained and tested more than 35,000 models using a unique new data set created for the challenge.

Follow NewsGram on Quora to get answers to all your questions.

Tested against a black box data set with challenging real world examples that were not shared with entrants, the top model achieved an average precision of 65.18 per cent.

Facebook partnered with other industry leaders and academic experts last year to create the Deepfake Detection Challenge.

“By creating and sharing a unique new data set of more than 100,000 videos, the DFDC has enabled experts from around the world to come together, benchmark their deepfake detection models, try new approaches, and learn from each others’ work,” the social network said in a statement.

Facebook AI model has achieved 65% accuracy to detect deepfake videos
Forged video of Facebook CEO Zuckerberg went viral last year. Wikimedia Commons

Facebook in January this year has announced tough policies against the spread of manipulated media on its platform.

The company said it will remove misleading manipulated media if it has been edited or synthesized beyond adjustments for clarity or quality.

Deepfakes are video forgeries that make people appear to be saying things they never did, like the popular forged videos of Facebook CEO Zuckerberg and that of US House Speaker Nancy Pelosi that went viral last year.

Also Read: Not Wearing Face Mask Increases Covid-19 Risk: Researchers

Videos that don’t meet standards for removal are still eligible for review by one of Facebook’s independent third-party fact-checkers, which include over 50 partners worldwide fact-checking in over 40 languages.

The compaby said it would also share details on its plans to open-source the raw data set used to construct the Deepfake Detection Challenge, featuring more than 3,500 actors and 38.5 days’ worth of data.

“This will help AI researchers develop new generation and detection methods to advance the state of the art in this field. Moreover, this data set will be opened for use for other research work in AI domains as well as work on deepfakes,” Facebook elaborated. (IANS)

STAY CONNECTED

19,152FansLike
362FollowersFollow
1,774FollowersFollow

Most Popular

Neglected Children More Likely To Have Teen Pregnancy: Study

Researchers have found that children who experience neglect are seven times more likely than other abuse victims to have a teen pregnancy. The study, published...

Sakharam Binder: Play That Explores Idea Of Censorship

Back in the early 1970s, Marathi playwright Vijay Tendulkar's play 'Sakharam Binder' -- which features the character of a bookbinder who 'takes in' women...

Patients With Covid-19 Likely To Diagnose With A Heart Stroke

Researchers have found that Covid-19 may be diagnosed on the same emergency scans intended to diagnose stroke. The findings published in the American Journal of...

Asian-Americans Experience Increased Racism Since Covid-19: Report

A report released by a US civil rights group showed Asian-Americans have experienced increased racism since the Covid-19 pandemic hit the country more than...

Hair Tips By Actress Kajol

Actress Kajol has often sported bouncy curls, and it is not too difficult to have hair like hers, she assures. Sharing a candid photo taken...

Twitter Halts Transparency Web Series Promotion. Is Twitter Biased?

By NewsGram Desk Twitter, a well-known platform to share ideas, thoughts, spread awareness, advertise our new ideas and projects, is suddenly taking down advertisements and...

Traditional Matchmaking Holds a Lot of Prejudiced, Preconceived Notions: Physician Rupam Kaur

By Siddhi Jain For Rupam Kaur, an Indian-American physician, the pursuit of finding love a second time took more than the traditional formula of meeting...

10 Facts on How Mosquitoes are One of the Deadliest Creatures in the World

A warmer climate, travel and trade are helping to spread mosquito-borne diseases as a deadly beast smaller than a paper clip poses a threat...

Recent Comments

Donate to NewsGram to support quality journalism.
x