Slashdot Mirror
New Password Recovery Technique Uses CPU and GPU Together
BaCa writes to mention that a new hardware/software combination has been created by a company called ElcomSoft that will reportedly allow cryptography professionals to build cheap PCs that work like supercomputers for the specific task of retrieving lost passwords. Utilizing a combination of the CPU and the GPU the task of brute forcing a password may be reduced by as much as a factor of 25. "Until recently, graphic cards' GPUs couldn't be used for applications such as password recovery. Older graphics chips could only perform floating-point calculations, and most cryptography algorithms require fixed-point mathematics. Today's chips can process fixed-point calculations. And with as much as 1.5 Gb of onboard video memory and up to 128 processing units, these powerful GPU chips are much more effective than CPUs in performing many of these calculations."
"Password Recovery" sounds so much more benign than "Cracking Passwords".
Hello, Mr. Orwell. *wave*
What seems to have been missed in the discussion so far is that this company is applying for a patent on their technique, which they claim is "revolutionary." I really hope that this doesn't get granted, as it would open a whole new realm of stupid patents for "X on a graphics card," which is about as stupid a patent as "X on the internet."
I'm not a security expert, but it seems to me that passwords are still useful in a variety of contexts, even if they can in principle be brute-forced. First of all, modern password systems should lock-down after multiple failed attempts (or use exponentially increasing lock-out intervals, or whatever). Furthermore, it should be obvious that the password hash itself should be guarded as much as possible. If done properly, this reduces the chances an attacker has to actually use a brute-force technique. (In which case, reasonably strong 8-character passwords already create an impossibly large parameter space to guess a password.)
I agree that other forms of authentication will become more commonplace, but I think passwords will continue to be used in a variety of circumstances. At a minimum, they will be no doubt continue to be used as part of some two-factor authentication systems.
FPGAs (Field-Programmable Gate Arrays) sound like they would be just the ticket for SIMD (single-instruction-multiple-data) calculations such as this. Configure up a bunch of FPGA chips to do the encryption calculations on a zillion combinations in parallel...
Paleotechnologist and connoisseur of pretty shiny things.
...why not just put the OS on the GPU and use the CPU for mundane things? :)
Camping on quad since 1996.
All password checks on my machines take 10 seconds minimum. A strategic 'sleep(10)' does the trick. There is no need to calculate MD5 hashes repeatedly to waste an attacker's time. A nice sleep() allows the server to go do something more useful.
Excuse me, but please get off my Pennisetum Clandestinum, eh!
The "sleep 10" idea is pretty much a waste of your time to code unless you also limit the number of incoming connections. It would be fine in the old days with a dedicated connection to a serial port on the back of the computer, but now all an attacker has to do is open up a few hundred connections to your machine and multiplex the attack. The attacker will not care that at any instant 99.9% of his connections are in the "sleep 10" state, as long as he can find one of the connections that is ready to accept another password.
http://utcc.utoronto.ca/~cks/space/blog/sysadmin/NetworkAuthDelays explains this issue, pointing out that all the delay does is annoy users who make typos, whilst not hurting attackers.
Because changing all instances of one character to another does nothing to protect your password. It takes much less processing power to run through all 'leetspeak' iterations of a dictionary attack than it does to brute force a password of similar length made of random characters.
Consider the number of possible 14-letter words or combinations of words and compare it to the number of possible random combinations. There are some thousands (or maybe millions) of words or combinations of words. Add in the substitution of digits for instances of some letters and you get (being generous here) a few hundred times more possible combinations. So, say 500 million combinations.
Now look at random 14 character strings. Even using only letters there are billions of billions of character combinations that are 14 characters long. By using words or strings of words you are cutting out nearly 100% of the possible passwords.
Besides, long series of random characters aren't really that difficult to remember. Just break them into patterns and remember the patterns.
Yes. It's terrible. All this company has done is use CUDA for what it was meant to be used. Big whoop. If they get a patent for it, it's really, really sad. And quite honestly, the number of passwords to test increases exponentially with length. It doesn't matter if they get a speed-up of 100x.
Except that you can't change the password when it's compromised.
Be nice to people on the way up. You will meet them again on your way down!