News for hackers. Stuff that matters.

A comment on Planting Undetectable Backdoors in Machine Learning Models. Parent comment

Re:Planting Undetectable Backdoors in Machine Learning Models by bboygravity on Sunday February 26, 2023 @02:58AM (#34943885)
> AWS is unlikely to intentionally modify your models to their benefit - mostly because

Except that it's essentially a given that it will happen, because why would the NSA not demand this? The have access to everything they want access to, why would they not want access to something so impactful? Even if to only use that access very rarely.

[ Parent | on HN ]
Re:Planting Undetectable Backdoors in Machine Learning Models by kmeisthax on Sunday February 26, 2023 @01:12PM (#34947760)
If you are worried about the NSA then you can't trust any viable AI training hardware either. If they can compromise AWS to alter your models then they can compromise Nvidia to change their drivers to do the same thing.
[ Parent | on HN ]