sabreW4K3@lazysoci.al to Technology@beehaw.org · 1 年前Astronomers discover technique to spot AI fakes using galaxy-measurement toolsarstechnica.comexternal-linkmessage-square24fedilinkarrow-up1121arrow-down10
arrow-up1121arrow-down1external-linkAstronomers discover technique to spot AI fakes using galaxy-measurement toolsarstechnica.comsabreW4K3@lazysoci.al to Technology@beehaw.org · 1 年前message-square24fedilink
minus-squareintensely_human@lemm.eecakelinkfedilinkarrow-up28·1 年前If there’s an algorithm for detecting deep fakes, there’s an algorithm for creating an AI capable of fooling that algorithm.
minus-squareTranquilTurbulence@lemmy.ziplinkfedilinkarrow-up5·11 个月前And then someone will create a new AI capable of defeating the old one. It’s just AIs all the way.
minus-squareintensely_human@lemm.eecakelinkfedilinkarrow-up4·11 个月前And they’ll train that AI on the first AI’s detection performance. This process is called Generative Adversarial Neural Networks, or GANN. It works really well and allows AI to become superhuman by having superhuman obstacles to overcome.
If there’s an algorithm for detecting deep fakes, there’s an algorithm for creating an AI capable of fooling that algorithm.
And then someone will create a new AI capable of defeating the old one. It’s just AIs all the way.
And they’ll train that AI on the first AI’s detection performance. This process is called Generative Adversarial Neural Networks, or GANN. It works really well and allows AI to become superhuman by having superhuman obstacles to overcome.