←back to thread

The Dangers of Microsoft Pluton

(gabrielsieben.tech)
733 points gjsman-1000 | 2 comments | 26 Jul 22 03:46 UTC | HN request time: 0s | source
Show context
trh0awayman ◴[26 Jul 22 06:33 UTC] No.32235082[source]▶
Can RISC-V save us here? Or is it time to start hoarding CPUs?
replies(3): >>32235107 #>>32235328 #>>32236432 #
zogomoox ◴[26 Jul 22 07:15 UTC] No.32235328[source]▶
I would assume chinese made RISC-V have their own special sauce.
replies(1): >>32235796 #
hammyhavoc ◴[26 Jul 22 08:38 UTC] No.32235796[source]▶
That's a big assumption.
replies(1): >>32236209 #
goodpoint ◴[26 Jul 22 09:45 UTC] No.32236209[source]▶
...if the schematics and tapeouts are entirely public.

Otherwise you can be assured that there will be backdoors.

replies(1): >>32236459 #
1. freemint ◴[26 Jul 22 10:27 UTC] No.32236459[source]▶
You can post hoc modify circuits so they look like doing logic A but they actually do logic B by adding new p or n junctions.
replies(1): >>32237598 #
2. goodpoint ◴[26 Jul 22 12:53 UTC] No.32237598[source]▶
In theory, yes. In practice it is not realistic to implement a plausible-deniable hardware backdoor targeting all CPUs being manufactured while keeping the schematics and tapeout open.

While the same CPUs are even fabbed in different locations around the world.

While also going undetected for years and while none of the engineers involved blows the whistle.

In short no, you can get away with a targeted attack but nothing so massive.