Re: the cold-boot attack - a paper tiger?

On 29.05.2008 20:56, [email protected] wrote:

> - to make use of semiconductor physics, key material would have to be stored on highly volatile level 1/2 CPU cache

I thought about this after writing the other mail.

I don't think the CPU kills it's cache after a reset.
Or at least "only" marks it as invalid.

So if i assume that the jumper on the reset-connector works:

Then the CPU isn't able to do anything while under permenant reset.

While the CPU is under permanent reset it should be possible to replace 
the BIOS-chip with someting of the attackers choosing.

When the jumper is removed the now BIOS should be the next thing that 
the CPU executes.

If i now assume that it is somehow possible to dump the CPU cache 
contents you can dump pretty much anything there is.

Conclusion: An attacker with enough resources should be able to get the 
whole memory contents with no or virtually no losses.



Bis denn

-- 
Real Programmers consider "what you see is what you get" to be just as 
bad a concept in Text Editors as it is in women. No, the Real Programmer
wants a "you asked for it, you got it" text editor -- complicated, 
cryptic, powerful, unforgiving, dangerous.


-
Linux-crypto:  cryptography in and on the Linux system
Archive:       http://mail.nl.linux.org/linux-crypto/