Combating deepfakes by confusing AI models with 'poisoned' data | ABC NEWS

Подробнее о видео

A new technique developed by the CSIRO combats the generation of deepfakes by 'poisoning' image data with invisible changes that confuse AI models.
Dr Liming Zhu says the technology could be applied in many areas, including the protection of sensitive data and intellectual property.
Subscribe:

ABC NEWS provides around the clock coverage of news events as they break in Australia and abroad. It's news when you want it, from Australia's most trusted news organisation.

For more from ABC NEWS, click here:
Watch more ABC NEWS content ad-free on ABC iview:

Go deeper on our ABC NEWS In-depth channel:
Like ABC NEWS on Facebook:
Follow ABC NEWS on Instagram:
Follow ABC NEWS on X (Twitter):

Note: In most cases, our captions are auto-generated.

#ABCNEWS #ABCNEWSAustralia #abcnewschannel