Page 1 of 1

PS3 - distributed tasks

Posted: Mon Apr 25, 2005 4:52 am
by Neila
It would be great to have a system like SETI-online, created for PS3 so we can harness the CELL power while we don't play.

I don't mean we need to look for aliens (only), but if there's an open system built for people fo form small clusters to solve particular problems will be great...

128bit encryption.. how long do you think will take...? :)

anyone what to start that project on SourceForge?

Re: PS3 - distributed tasks

Posted: Mon Apr 25, 2005 5:14 am
by Shine
Neila wrote: 128bit encryption.. how long do you think will take...? :)
If you need to check every key, there are 2^128 keys. Assuming you have 1 billion PS3, where each one can check 1 million keys per second, you'll need only 10790283070806014 years.

Posted: Mon Apr 25, 2005 5:20 am
by Neil Stevens
If all it took to crack 128-bit symmetric encryption was a piece of hardware that can be sold for the mass market, then AES would have been created with a much bigger key.

Posted: Mon Apr 25, 2005 6:03 am
by Neila
ok.. forget the key, that was not the idea =/

Posted: Tue Apr 26, 2005 1:57 am
by Neila
besides, why use a brute-force when you can use something like:

...The standard techniques of differential and linear cryptanalysis can be adapted to be used against AES. Because of the way matrix multiplication works, and because in GF(2^8), all the coefficients of the Mix Column matrix (as indeed all numbers from 1 to 255) have reciprocals, a specific attack, originally developed for use against its predecessor Square, called the "Square attack", can be used as well.

If one uses 256 blocks of chosen plaintext, where every byte but one is held constant, and that one is given all 256 possible values, then after one round of AES, four bytes will go through all 256 possible values, and the rest of the bytes will remain constant. After a second round, sixteen bytes will each go through all 256 possible values, without a single duplicate, in the encipherment of the 256 blocks of chosen plaintext. (For a 128-bit block, this is every byte; for larger blocks, the rest of the bytes will remain constant.) This interesting property, although not trivial to exploit, can be used to impose certain conditions on the key when one additional round, before or after the two rounds involved, is present.

The possibility of this attack was noted in the paper that initially described Square....

more here:
http://home.ecn.ab.ca/~jsavard/crypto/co040401.htm

Posted: Tue Apr 26, 2005 4:20 am
by Neil Stevens
Surely if the attack was known in Square, then the Rijndael creators and/or the AES committee added enough rounds to the AES spec to defeat the attack?

Ah, I see. 256 blocks of chosen plaintext. Definitely practical in some circumstances against broken cryptographic implementations. NOT useful in the PSP-related AES discussions elsewhere on this site, heh.

Posted: Wed Apr 27, 2005 12:03 pm
by Neila
we have encrypted 128 bit block in test.bin
it's a good bet that there are only a few chars in the original.

But if you say so, I would not recomend to anyone to try to implement something like that because it may be Illigal.

I just wanted to give the idea of creating dictributed architecture for the PS3, and whoever wants to modify it to search aliens, or look for the human g-nome or whatever, to be able to do it with ease.