Fooling deepfake detectors is possible according to American scientists


The uncompressed videos were more than 99% successful in deceiving the deepfake detectors in cases where the attacker had access to all the parameters, the scientists reported. — AFP Relaxnews

Deepfakes still have a bright future ahead of them, it would seem. It is still possible to thwart the recognition of deepfakes by even the most highly developed detectors, according to scientists at the University of San Diego. By inserting "adversarial examples" into each frame, artificial intelligence can be fooled. An alarming observation for scientists who are pushing to improve detection systems to better detect these faked videos.

During the last WACV 2021 (Winter Conference on Applications of Computer Vision), which took place from Jan 5 to 9, scientists from the University of San Diego have demonstrated that deepfake detectors have a weak point.

According to these professionals, by using "adversarial examples" in each shot of the video, artificial intelligence could make a mistake and designate a deepfake video as true.

These "adversarial examples" are in fact slightly manipulated inputs that can cause the artificial intelligence to make mistakes. To recognise deepfakes, the detectors focus on facial features, especially eye movement like blinking, which is usually poorly reproduced in these fake videos.

Subscribe now and receive FREE sooka plan for 1 month.
T&C applies.

Monthly Plan

RM13.90/month

Annual Plan

RM12.33/month

Billed as RM148.00/year

1 month

Free Trial

For new subscribers only


Cancel anytime. No ads. Auto-renewal. Unlimited access to the web and app. Personalised features. Members rewards.
Follow us on our official WhatsApp channel for breaking news alerts and key updates!

Deepfake

   

Next In Tech News

World's first wooden satellite, developed in Japan, heads to space
This humanoid robot can now operate with full autonomy
Scientists use AI to help track penguins in Antarctica
Windows 10 users will soon have to pay to keep getting security updates
Musk and X are epicenter of US election misinformation, experts say
OpenAI in talks with California to become for-profit company, Bloomberg News reports
Meta to extend ban on new political ads after U.S. election
Crypto firms including Robinhood, Kraken launch global stablecoin network
Chipmaker NXP forecasts quarterly revenue below estimates on macroeconomic concerns
Exclusive-Silver Lake, Bain prepare to bid for multi-billion stake in Intel's Altera unit, sources say

Others Also Read