25-GPU cluster cracks every standard Windows password in less than 6 hours

http://arstechnica.com/security/2012/12/25-gpu-cluster-cracks-every-standard-windows-password-in-6-hours/

by rayval • 14 years ago

113 70 14 years ago

arstechnica.com

rayval2• 14 years ago

Edited title for length, because original title got truncated in a confusing fashion.

Original title: "25-GPU cluster cracks every standard Windows password in <6 hours"

rayval2• 14 years ago

Looks like that got fixed by sysop gods. Thanks!

patrickgzill2• 14 years ago

If this is done with commodity hardware, now, what were the NSA's capabilities even 5 years ago?

SenorWilson• 14 years ago

I'm sure they were able to crack the encryption method before Microsoft started using it.

bradleyland• 14 years ago

Put your tin foil hats away. This doesn't "crack" NTLM, it brute forces at a very high rate. The NSA has more money to spend, but are similarly limited by the hardware available at any given point.

apawloski6• 14 years ago

For comparison, a couple weeks ago Oak Ridge National Laboratory's Titan computer topped the Top500 list for fastest supercomputer in the world (although that title is a bit misleading). Here's the specs on Titan:

18,688 AMD Opteron 6274 16-core CPUs

18,688 Nvidia Tesla K20 GPUs

17.59 petaflops

Titan displaced Sequoia (at Lawrence Livermore National Laboratory) from the top spot on Top500. Interestingly enough, Sequoia uses a very different architecture, based on 16-core PowerPC A2 nodes rather than GPUs. Sequoia also has about 1.6PB of memory, while Titan "only" has 1PB.

Both computers have reasonably different use cases. GPUs are great for embarrassingly parallel, non-memory intensive tasks like brute forcing passwords. But all of the rumors about the NSA's massive data analysis needs suggests that they may need a cluster that resembles Sequoia (with fewer cores, but larger caches and available memory) more than Titan.

muyuu3• 14 years ago

I wouldn't call a big cluster of commodity hardware simply commodity hardware because then many of the top supercomputers of the world are commodity hardware.

The combination is exotic enough to be considered non-commodity hardware.

recoiledsnake• 14 years ago

Every standard Windows password less than 8 chars only?

apawloski6• 14 years ago

I know for practical purposes this doesn't seem like that big of a deal, but you have to understand that 8 chars of mixed case, numbers, and symbols is still a gigantic key space. That this can be done so quickly on commodity hardware is pretty impressive.

hayksaakian2• 14 years ago

Individual char variance is less significant compared to additional chars.

Look at the xkcd password entropy comic

jiggy20115• 14 years ago

Some versions of Windows (XP and lower I believe?) would split long passwords into 2 hashes, effectively allowing them to be cracked in parallel.

namank• 14 years ago

How bout SSL?

cynwoody• 14 years ago

Impressive as the numbers are, it's worth remembering that this is an "offline crack", going against a stolen list of encrypted passwords. If they can steal your database of encrypted passwords, you've got a problem no matter how strong the passwords are.

How many guesses per second do you get in a typical online crack? E.g., a script kiddie trying to guess your cloud server's SSH password?

ramidarigaz3• 14 years ago

On my webserver, you get 3 chances and then a 24 hour ip ban. I think that comes out to 0.00003 passwords per second :)

The particularly persistent IPs get a special iptables rule.

obilgic• 14 years ago

Could you share the details of the implementation please?

cgag• 14 years ago

I suppose it's a bit different from a user facing login, but does anyone know why these limits tend to be set so low? I've locked myself out of plenty of things, and so have plenty of people I know. It seems like setting the limit to 20 would be just as effective in blocking brute force attacks without being user unfriendly.

Is it that with user facing services the common user/passwords are so common it's reasonable to just try just the top x most common passwords?

Zenst• 14 years ago

I remember using the nice fingerprint reader upon my old IBM laptop once, worked well until you changed your password and then if you had not updated the one in finger print encypted libary you got some impressive automation. Usualy it would automate yoru password once you scanned your finger. Now with the power of a computer you could scan your finger once and watch as the wonderful system tried the wrong password as fast as it could repeat upon itself. Was fun restoring my blackberry from backup after the 10 failed attempts in nanoseconds.

I like your approach though though I would redirect them to a appeal process that a human could read, but I'm not aware of the volumes you have to deal with. I would though wonder how this system will adapt come IPV6 times and with that if your not using it then I hope it is disabled as if your ISP/provider suddenly starts processing it or running tests then that latent IPV6 stack doing nothing could suddenly come to life and you probably don't have many firewall or IPtable rules for that in place. But that is a problem many will face over the years comming.

Symmetry• 14 years ago

That's why an attacker will try three common passwords against every possible login name.

mitchi• 14 years ago

These hash functions are made to be fast to hash :P Check out the NIST competition, they picked the fastest hash that can be calculated with special hardware :) People who want real offline password security should use slow hash functions (and passphrases of course).

plaguuuuuu2• 14 years ago

it's my understanding that NTLM hashes are sent over the wire...? therefore any machine on the local network could intercept this hash via network-level attacks such as ARP poisoning, WiFi attacks, etc. Then the cracking box would quite happily and easily brute force the entire 8 char keyspace and reveal the pass.

it's a different threat model to hash+email retrieval via sql injection which can lead to all sorts of nastiness involving hijacking email and then other accts

jiggy20115• 14 years ago

If they are sent over the wire I hope there is some additional encryption such as SSL involved in the transmission!

Otherwise regardless of hash crackability, one would be able to do authentication bypass by simply sniffing hashes and replaying them.

iamchrisle• 14 years ago

Nice. But can it run Crysis?

rtkwe• 14 years ago

Yes. Physically, it's running *nix though so you'd have to get windows to not freak out with all that power.

jwilliams• 14 years ago

This was discussed 3-4 days ago: http://news.ycombinator.com/item?id=4875206

Upshot - it's impressive, but NTLM already known as an vulnerable target.

madao• 14 years ago

I remember back when I was doing a network engineering course the guys could crack a windows password in minutes offline, simple matter of grabbing the database from the machine. I think once you have the machine offline unless you encrypt the data your pretty screwed regardless..

Blara• 14 years ago

When was this? I know older windows versions stored passwords in plain text... I can't remember when they switched to hashed passwords but I think it was around XP or Vista

muyuu3• 14 years ago

Windows never stored system passwords in plain text.

It did use the LM hash function to store passwords, which was rather weak, making rainbow table attacks easy.

http://en.wikipedia.org/wiki/LM_hash

For backwards compatible this hash function was commonly in use up to Windows 7 (it was disabled by default in Vista though). There are decent workarounds since NT.

NTLMv1 is also rather easy to crack. NTLMv2 is better but took a long time to be in wide use. Kerberos is strong too and can be used

Long story short, Windows OS prior to Vista maintain weaker hash support for backwards compatibility by default (although you can work around it since NT 4, almost nobody did this). Windows Vista still has support for them if you want to turn it on, but by default it's off. From Windows 7 there is no support for weak system hashes. For Active Directories, MIT's Kerberos (used typically in Unix networked environments since the 80s) replaced NTLM from Windows 2000 on.

jiggy20115• 14 years ago

You might be thinking of a very old version of Windows, like 3.1 vintage.

3.1 didn't really have passwords to access the system, it did however have screensaver passwords which were either plain text or a very weak hash.

They could also be disabled by simply deleting the line for a .ini file which was bad considering it didn't have the concept of users who could only access certain files.

rjempson2• 14 years ago

I'm not sure there is much significance to this article.

It points out "The technique doesn't apply to online attacks, because, among other reasons, most websites limit the number of guesses that can be made for a given account."

Same applies to Windows.

rjempson2• 14 years ago

Thinking about it some more. Is the only practical exploit of this the case where a rogue sysadmin wants to figure out user passwords (without resetting the password and therefore alerting the user)?

ramblerman• 14 years ago

I think what they're referring to is having access to the physicial harddisk. In linux terms it would equate to having a copy of the /etc/passwd file.

For example the FBI seizes someones computer. This would allow them to brute force without said restriction.

So yes, from an online, or standard entry viewpoint this is a moot point. Also a properly encrypted hard drive using something like truecrypt is still pretty impenetrable regardless.

halviti• 14 years ago

I've grabbed the SAM file from remote IIS servers in my younger years and cracked the passwords locally.

Buffer overflow the web service, bind a command shell to a port running as the system account (by having the system execute shellcode used in the buffer overflow), netcat to your open port, ftp the SAM (located in the repair directory) to somewhere you can retrieve it, download the file, delete all of the logs, crack the file.

Hard drive encryption would have done nothing to prevent this.

jiggy20115• 14 years ago

Technically you want /etc/shadow as that is where the actual hashes are stored.

On a Linux system usually any user has at least read access to /etc/passwd but only root has /etc/shadow.

This attack would presume that you already have either physical access to the disk or you have already compromised the machine remotely to basically root or admin type level.

Of course being able to get the actual passwords of users would be useful to an attacker because they might be able to use them to elevate from access to one system to potentially other systems where users might well be using the same password.

Not sure how drive encryption with Truecrypt would work in this case. I presume password hashes are stored outside of the encrypted part otherwise every user would have to enter the volume key before they signed in regardless of their access level. Which would mean distributing the volume key widely.

Truecrypt is also vulnerable in the sense that it is often possible to grab the volume key straight out of DRAM if the computer is on or has only recently been switched off.

pserwylo2• 14 years ago

I disagree. If a website gets hacked and its customer database is stolen, then this could be used to crack the user passwords.

jasonwatkinspdx• 14 years ago

Offline attacks matter. The last few years have seen a continuous stream of high profile account database leaks. There are now some 1 billion known real user selected passwords that are readily downloaded from any of a number of shady sites.

It is irrational to assume that password database leaks won't continue.

The hashing scheme and salting matters less and less, as the total entropy humans can conveniently recall is quite limited and moore's law keeps marching.

We need a fundamental rethinking of security and identity on the internet, and IMHO the OSS world needs to get there before partisan commercial interestes.

pserwylo2• 14 years ago

I saw a talk on Mozilla Persona [0] the other day from one of the devs. I like the idea of these decentralised authentication systems. I was (and still am a fan of) OpenId too.

There is no practical reason that website operators need to know that a user typed in the right password, only that they are who they say they are. Anything which is able to prove this (to a satisfactory level) with the least amount of information being stored by the website is good in my books.

[0] https://www.mozilla.org/persona

peteretep• 14 years ago

Less good against non-NTLM passwords ... from my comment last time:

Taking SHA-1 (which YOU MUST NOT USE for password hashing blah), it only manages 63 billion a second. To try all the passwords for that in the alphanumeric space:

- 10 chars: 35 weeks

- 11 chars: 44 years

- 12 chars: 2,800 years

- 16 chars: 11 times the age of the sun

10 chars for bcrypt: 600,000 years...

http://www.wolframalpha.com/input/?i=%2865**16+%2F+63+billio...

muyuu3• 14 years ago

http://www.imdb.com/title/tt0109686/quotes?qt=qt0383410

Lloyd: What are my chances?

Mary: Not good.

Lloyd: You mean, not good like one out of a hundred?

Mary: I'd say more like one out of a million.

[pause]

Lloyd: So you're telling me there's a chance... YEAH!

joshmaker• 14 years ago

- 8 chars: 84 minutes

- 6 chars: 1.2 seconds

All of which demonstrates the importance of requiring longer passwords. Also, keep in mind that these are maximum times required to crack a password and not the average times.

mikeash• 14 years ago

The average time to crack will just be half of the maximum, so it's not a big difference (compared to order of magnitude errors, anyway). Still good to point out, though.

ChrisNorstrom• 14 years ago

Guess what? Back in 2009, I started using a method to remember long passwords with a huge # of letters, numbers, & special characters.

Gw?Bi2009Isuamtrlpwah#ol,n,&sc. (31 characters)

Create memorable sentences and create a password using the first letter of each word & all the numbers and punctuation. After entering it 10 or so times you'll get used to it pretty quickly.

phpnode4• 14 years ago

or you can literally write the whole sentence, which is even more secure and you don't have to remember any special rules, just the sentence itself. Of course it's more typing:

    Guess what? Back in 2009 I saw a uniquely attired man traipsing round local places with a high number of legs, necks and shirt collars.

136 characters or 14 Gigayears to crack. Wow today I learnt that there's such a thing as a Gigayear.

sunraa• 14 years ago

I just went through the process of changing passwords to sentences. You'd be surprised at how many sites do not allow sentences.

apawloski6• 14 years ago

Well, to be fair, 14 Gigayears in terms of an attack geared towards a totally different case. I wonder if we can optimize an attack on sentence passwords using hidden markov modeling, or other natural language processing methods. The entropy at the character level decreases if we assume the password is an english sentence [1], and my gut feeling is that we can apply this same thinking at the word level as well (this may very well have been demonstrated already in research).

[1] http://www.nd.edu/~busiforc/handouts/cryptography/cryptograp...

16s• 14 years ago

NTLM hashes are stored in Active Directory servers as one round of unsalted MD4. It's plain MD4. Not many people know this and I only point it out as it's important to understand that when talking about how many cracks per second they are getting.

jiggy20115• 14 years ago

So , why don't modern versions of Windows just use Bcrypt or similar for passwords?

25-GPU cluster cracks every standard Windows password in less than 6 hours

Related Stories