iaik / flush_flush Goto Github PK

I can't build the useful eviction set for Prime+Prome attack, since my intel version is i7-11800H equipped with Tiger Lake-H architecture. Can someone share your cpu version which can successfully perform this attack ?

I'm trying to execute the calibration.c file place in /histrogram/pp but it give me a segmentation fault when it try to execute line 126. Should I change something to make it work?

When I changed the key, the output is still the same.


the result is

When i calculated the T-table addresses they are in increasing order from Te0 to Te3. The code you have given have it in reverse order. Execution is throwing segmentation fault even when in code addresses are set in decreasing order only.

Hello, I am getting this when I try to compile the flush flush calibration utility:
error: inconsistent operand constraints in an ‘asm’ on a VM. (I can compile it on my local)
Info of my system:
[07/14/18]seed@VM:~/.../ff$ lsb_release -a No LSB modules are available. Distributor ID: Ubuntu Description: Ubuntu 16.04.2 LTS Release: 16.04 Codename: xenial [07/14/18]seed@VM:~/.../ff$ uname -a Linux VM 4.8.0-36-generic #36~16.04.1-Ubuntu SMP Sun Feb 5 09:39:41 UTC 2017 i686 i686 i686 GNU/Linux [07/14/18]seed@VM:~/.../ff$ gcc --version gcc (Ubuntu 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 Copyright (C) 2015 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
I read in other places that this is a common error related with gcc and it was supposed to be patched for gcc versions > 5. I have the same OS and same gcc version on my local machine, in which it does compiles. Could it be the kernel version?
Thank you for your time.

Respected Sir,

What do you mean by "self-compiled OpenSSL library" mentioned under "OpenSSL AES T-Table attack" section? and how do I create "self-compiled OpenSSL library"?

How do I enable it's T-Table-based AES implementation?

kindly guide us in this regard. Thanking you

Even after updating T-tables address as per decreasing order (After reversing the tables address from Te3 to Te0) and as root.

Has anyone know the cache slice reverse engineeering function for KabyLake microprocessor or how to get it?

Thanks a lot for your source code. When I run histogram/ff/calibration, I find that the time difference is more than 100. However, the time difference stated in the original paper is only about 10 cycles.

While executing ./spy in prime+probe attack code throws segmentation fault.

./spy /usr/lib/x86_64-linux-gnu/libgdk-3.so.0.1200.2 0x85ec0 # use a suitable address .

Where do i get this suitable address?