sabreW4K3@lazysoci.al to Technology@beehaw.org · 4 months agoAstronomers discover technique to spot AI fakes using galaxy-measurement toolsarstechnica.comexternal-linkmessage-square25fedilinkarrow-up1120arrow-down10cross-posted to: artificial_intel@lemmy.ml
arrow-up1120arrow-down1external-linkAstronomers discover technique to spot AI fakes using galaxy-measurement toolsarstechnica.comsabreW4K3@lazysoci.al to Technology@beehaw.org · 4 months agomessage-square25fedilinkcross-posted to: artificial_intel@lemmy.ml
minus-squareintensely_human@lemm.eelinkfedilinkarrow-up25·4 months agoIf 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-up4·4 months agoAnd then someone will create a new AI capable of defeating the old one. It’s just AIs all the way.
minus-squareintensely_human@lemm.eelinkfedilinkarrow-up4·4 months agoAnd 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.