* Re: Guidelines for pre-trained ML model weight binaries
@ 2023-09-12 7:36 Nathan Dehnel
0 siblings, 0 replies; 2+ messages in thread
From: Nathan Dehnel @ 2023-09-12 7:36 UTC (permalink / raw)
To: Andreas Enge, guix-devel
That was fascinating, thanks for sharing.
^ permalink raw reply [flat|nested] 2+ messages in thread
* Guidelines for pre-trained ML model weight binaries (Was re: Where should we put machine learning model parameters?)
@ 2023-04-07 5:50 Nathan Dehnel
2023-09-06 14:28 ` Guidelines for pre-trained ML model weight binaries Andreas Enge
0 siblings, 1 reply; 2+ messages in thread
From: Nathan Dehnel @ 2023-04-07 5:50 UTC (permalink / raw)
To: rprior, guix-devel
I am uncomfortable with including ML models without their training
data available. It is possible to hide backdoors in them.
https://www.quantamagazine.org/cryptographers-show-how-to-hide-invisible-backdoors-in-ai-20230302/
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2023-09-12 7:37 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2023-09-12 7:36 Guidelines for pre-trained ML model weight binaries Nathan Dehnel
-- strict thread matches above, loose matches on Subject: below --
2023-04-07 5:50 Guidelines for pre-trained ML model weight binaries (Was re: Where should we put machine learning model parameters?) Nathan Dehnel
2023-09-06 14:28 ` Guidelines for pre-trained ML model weight binaries Andreas Enge
Code repositories for project(s) associated with this public inbox
https://git.savannah.gnu.org/cgit/guix.git
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).