| |||||||||||||
Random instruction timingsRandom instruction timingsPosted Oct 6, 2009 9:06 UTC (Tue) by dlang (✭ supporter ✭, #313)In reply to: Random instruction timings by kleptog Parent article: Scenes from the Real Time Linux Workshop
this brings into question the tactic of checking timing to see what commands were executed by other processes in order to guess encryption keys. (along with things like measuring power consumption, etc as well)
you may be able to do this on simple CPUs used for embedded applications, but this makes it pretty clear that this path of attack is not that big a risk on current x86 cpus
(Log in to post comments)
Random instruction timings Posted Oct 8, 2009 14:01 UTC (Thu) by jzbiciak (✭ supporter ✭, #5246) [Link]
The magnitude of an external cache miss is still high enough that I imagine you could see its signature even over the LS-bit noise in the TSC. It may take several runs to correlate things well enough, though, so an isolated encryption event may still hide in the noise.
|
|||||||||||||