D_a_X@feddit.org to Netzkultur / Netzpolitik@feddit.org · 1 month agoLLMs can unmask pseudonymous users at scale with surprising accuracy - Ars Technicaarstechnica.comexternal-linkmessage-square2linkfedilinkarrow-up128arrow-down11file-textcross-posted to: privacy@programming.devfuck_ai@lemmy.worldtechnik@feddit.orgprivacy@programming.devprivacy@lemmy.dbzer0.comprivacy@lemmy.worldtechnology@lemmy.ziptechnologie@jlai.luhackernews@lemmy.bestiver.se
arrow-up127arrow-down1external-linkLLMs can unmask pseudonymous users at scale with surprising accuracy - Ars Technicaarstechnica.comD_a_X@feddit.org to Netzkultur / Netzpolitik@feddit.org · 1 month agomessage-square2linkfedilinkfile-textcross-posted to: privacy@programming.devfuck_ai@lemmy.worldtechnik@feddit.orgprivacy@programming.devprivacy@lemmy.dbzer0.comprivacy@lemmy.worldtechnology@lemmy.ziptechnologie@jlai.luhackernews@lemmy.bestiver.se
minus-squareKairos@lemmy.todaylinkfedilinkarrow-up6·1 month agoHi. Resident skeptic here. How did they make the data? There’s effectively zero way to run this on real accounts (no way to verify correctness) so I’m thinking that the researchers made accounts that aren’t realistic.
minus-squareGeneral_Effort@lemmy.worldlinkfedilinkarrow-up1·1 month agohttps://arxiv.org/abs/2602.16800
Hi. Resident skeptic here. How did they make the data? There’s effectively zero way to run this on real accounts (no way to verify correctness) so I’m thinking that the researchers made accounts that aren’t realistic.
https://arxiv.org/abs/2602.16800