Planning to build a 8 GPU password cracking server.
7 minutes ago, TwoBigBalls said:Obviously for research purposes.
As far as optimization goes and utilizing the best of what you have, 1080ti's seem to be "king" for this. Personally I use two with 1100kh-1200kh/s for testing my own network. Can't complain, but without knowing what hardware you want/need I think you'll be more limited by your capabilities to understand the software you use.
See : https://hashcat.net/wiki/doku.php?id=mask_attack
I would recommend building your own skillset before dropping a pretty dime on such hardware.
In traditional Brute-Force attack we require a charset that contains all upper-case letters, all lower-case letters and all digits (aka “mixalpha-numeric”). The Password length is 9, so we have to iterate through 62^9 (13.537.086.546.263.552) combinations. Lets say we crack with a rate of 100M/s, this requires more than 4 years to complete. In Mask attack we know about humans and how they design passwords. The above password matches a simple but common pattern. A name and year appended to it. We can also configure the attack to try the upper-case letters only on the first position. It is very uncommon to see an upper-case letter only in the second or the third position. To make it short, with Mask attack we can reduce the keyspace to 52*26*26*26*26*10*10*10*10 (237.627.520.000) combinations. With the same cracking rate of 100M/s, this requires just 40 minutes to complete.
Good start, OP should be aware there are more methods than this too : D
4 minutes ago, TwoBigBalls said:Just stalked this guys profile a bit.
He checks out.
lol thanks
I ended up with a distributed solution. For about ~$1400 I got performance in the range of 35-40GH/s on MD5. Not too bad, but at least it's scalable as I had to spend some on setting up the network to allow for future upgrades. Should be able to support about 2 or 3 more GPUs before having to buy another motherboard and other PC stuff.