return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 1 day agoLLMs can unmask pseudonymous users at scale with surprising accuracyarstechnica.comexternal-linkmessage-square91linkfedilinkarrow-up1293arrow-down111cross-posted to: cybersecurity@sh.itjust.works
arrow-up1282arrow-down1external-linkLLMs can unmask pseudonymous users at scale with surprising accuracyarstechnica.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 1 day agomessage-square91linkfedilinkcross-posted to: cybersecurity@sh.itjust.works
minus-squareGeneral_Effort@lemmy.worldlinkfedilinkEnglisharrow-up1·6 hours agoHmm. Maybe but it is not the same problem as those discussed in OP. I also have some doubts about the paper, but that’s another story. You could try it out?
minus-squareFauxPseudo @lemmy.worldlinkfedilinkEnglisharrow-up1·3 hours agoI’m not qualified to design the prompts and home users can’t really pile in 3 million+ documents.
Hmm. Maybe but it is not the same problem as those discussed in OP. I also have some doubts about the paper, but that’s another story. You could try it out?
I’m not qualified to design the prompts and home users can’t really pile in 3 million+ documents.