Is It EVEN Possible To Reverse Engineer AI’s Training Data?

Deploy on Sevalla now and get a free $50 credit!
https://sevalla.com/?utm_source=ByCloud's&utm_medium=Referral&utm_campaign=youtube


In this video, we dive into how much of the private training data researchers can infer or approximate.

My Newsletter
https://mail.bycloud.ai/

my project: find, discover & explain AI research semantically
https://findmypapers.ai/

My Patreon
https://www.patreon.com/c/bycloud


Can We Infer Confidential Properties of Training Data from LLMs?
[Paper] https://arxiv.org/abs/2506.10364

Interpreting the Repeated Token Phenomenon in LLMs
[Paper] https://arxiv.org/abs/2503.08908

Approximating Language Model Training Data from Weights
[Paper] https://arxiv.org/abs/2506.15553


Try out my new fav place to learn how to code https://scrimba.com/?via=bycloudAI

This video is supported by the kind Patrons & YouTube Members:
🙏Nous Research, Chris LeDoux, Ben Shaener, DX Research Group, Poof N' Inu, Andrew Lescelius, Deagan, Robert Zawiasa, Ryszard Warzocha, Tobe2d, Louis Muk, Akkusativ, Kevin Tai, Mark Buckler, NO U, Tony Jimenez, Ângelo Fonseca, jiye, Anushka, Asad Dhamani, Binnie Yiu, Calvin Yan, Clayton Ford, Diego Silva, Etrotta, Gonzalo Fidalgo, Handenon, Hector, Jake Disco very, Michael Brenner, Nilly K, OlegWock, Daddy Wen, Shuhong Chen, Sid_Cipher, Stefan Lorenz, Sup, tantan assawade, Thipok Tham, Thomas Di Martino, Thomas Lin, Richárd Nagyfi, Paperboy, mika, Leo, Berhane-Meskel, Kadhai Pesalam, mayssam, Bill Mangrum, nyaa,
Toru Mon


[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[Business Inquiries] bycloud@smoothmedia.co
[Profile & Banner Art] https://twitter.com/pygm7
[Video Editor] @Booga04