Live data from Hacker News

Downfall Attacks

downfall.page

1–10 of 349 posts

Re: Downfall Attacks

#4
From FAQ: [Q] How long have users been exposed to this vulnerability? [A] At least nine years. The affected processors have been around since 2014.

Amazing how these vulnerabilities sit around unnoticed for years and then it takes two weeks for someone to code up an exploit.

Re: Downfall Attacks

#5
post #4

From FAQ: [Q] How long have users been exposed to this vulnerability? [A] At least nine years. The affected processors have been around since 2014. Amazing how these vulnerabilities sit around unnoticed for years and then it takes two weeks for someone to code up an exploit.

I have a feeling the time spent searching for the vulnerability in the first place was more than 2 weeks though.

Re: Downfall Attacks

#6
post #2

This is a huge performance hit - up to 50% it is claimed! 70% of modern intel processors are affected apparently as well.

> some workloads may experience up to 50% overhead

They word there are "some workloads", I suspect that performance hit is rare.

Re: Downfall Attacks

#7
post #3

Geez! This seems like a _really_ big attack vector. Anyone on the security side have some caveats?

If I'm reading this right, the caveat is that the exploit only lets you read registers that have been saved for context-switching.

So, in order to extract data, that data must be in constant active use (i.e. loaded in a register) at the time of the attack.

Re: Downfall Attacks

#9
post #7
post #3

Geez! This seems like a _really_ big attack vector. Anyone on the security side have some caveats?

If I'm reading this right, the caveat is that the exploit only lets you read registers that have been saved for context-switching. So, in order to extract data, that data must be in constant active use (i.e. loaded in a register) at the time of the attack.

Would environmental variables be something that shows up in context-switching?
Post reply on HN