Vulnerabilities / Threats
8/16/2010
01:37 PM
50%
50%

Passwords Quickly Hacked With PC Graphics Cards

Georgia Tech researchers find that high-end, readily available graphics processing units are powerful enough to easily crack secret codes.




Slideshow: Cloud Security Pros And Cons
(click for larger image and for full photo gallery)
Passwords with fewer than 12 characters can be quickly brute-force decoded using a PC graphics processing unit (GPU) that costs just a few hundred dollars, according to researchers at the Georgia Institute of Technology.

"We've been using a commonly available graphics processor to test the integrity of typical passwords of the kind in use here at Georgia Tech and many other places," said Richard Boyd, a senior research scientist at the university's research institute, in a statement. "Right now we can confidently say that a seven-character password is hopelessly inadequate."

Today's top graphics processors offer about two teraflops of parallel processing power. For comparison, "in the year 2000, the world's fastest supercomputer, a cluster of linked machines costing $110 million, operated at slightly more than 7 teraflops," he said.

The barrier to using multi-core graphics processors -- available from Nvidia or AMD's ATI division -- for compute-intensive processes other than graphics processing, said Boyd, first fell in 2007, when Nvidia released a C-based software development kit. "Once Nvidia did that, interest in GPUs really started taking off," he said. "If you can write a C program, you can program a GPU now." Or use it to crack a password.

Furthermore, thanks to Moore's Law, graphics processors continue to increase in power, which means that GPUs will get better, not worse, at cracking passwords.

But who needs a graphics processor? People often create and rely on simple passwords, and many websites use passwords more for psychological than security purposes.

But the Georgia Tech research underscores the importance of getting people to adopt longer, non-simple passwords to make them safer against attack. "Length is a major factor in protecting against 'brute forcing' a password," according to one research scientist involved in the project, Joshua Davis. "A computer keyboard contains 95 characters, and every time you add another character, your protection goes up exponentially, by 95 times."

For the record, to defend against GPU attacks, the password researchers recommend using sentence-length passwords that mix letters with numbers or symbols, and which are at least 12 characters long.

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
ANON1241631011972
50%
50%
ANON1241631011972,
User Rank: Apprentice
11/1/2011 | 6:35:42 PM
re: Passwords Quickly Hacked With PC Graphics Cards
I think this article overstates the capabilities and the use case does not generally exist in the real world. Passwords do not exist in a cyberspace vacuum, just waiting to be attacked in isolation. They exist in combination with a user identifier and a challenge/response system behind a UI. While the brute force methods may be capable of generating all the possible combinations, they still have to test them against a validation challenge with the correct response set. Most password challenge systems have two additional inhibitors against brute force attacks: 1. They don't respond at GPU speeds 2. They usually disable the account after 3 to 5 failed attempts. So, unless the brute force program has the password database available and the appropriate decode algorithms to provide the correct challenge/response patterns, it will not succeed. If the attacker has that kind of access, he or she is already past the firewall and well into the bowels of the network.
Register for Dark Reading Newsletters
White Papers
Cartoon
Current Issue
Flash Poll
Video
Slideshows
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2014-9710
Published: 2015-05-27
The Btrfs implementation in the Linux kernel before 3.19 does not ensure that the visible xattr state is consistent with a requested replacement, which allows local users to bypass intended ACL settings and gain privileges via standard filesystem operations (1) during an xattr-replacement time windo...

CVE-2014-9715
Published: 2015-05-27
include/net/netfilter/nf_conntrack_extend.h in the netfilter subsystem in the Linux kernel before 3.14.5 uses an insufficiently large data type for certain extension data, which allows local users to cause a denial of service (NULL pointer dereference and OOPS) via outbound network traffic that trig...

CVE-2015-2666
Published: 2015-05-27
Stack-based buffer overflow in the get_matching_model_microcode function in arch/x86/kernel/cpu/microcode/intel_early.c in the Linux kernel before 4.0 allows context-dependent attackers to gain privileges by constructing a crafted microcode header and leveraging root privileges for write access to t...

CVE-2015-2830
Published: 2015-05-27
arch/x86/kernel/entry_64.S in the Linux kernel before 3.19.2 does not prevent the TS_COMPAT flag from reaching a user-mode task, which might allow local users to bypass the seccomp or audit protection mechanism via a crafted application that uses the (1) fork or (2) close system call, as demonstrate...

CVE-2015-2922
Published: 2015-05-27
The ndisc_router_discovery function in net/ipv6/ndisc.c in the Neighbor Discovery (ND) protocol implementation in the IPv6 stack in the Linux kernel before 3.19.6 allows remote attackers to reconfigure a hop-limit setting via a small hop_limit value in a Router Advertisement (RA) message.

Dark Reading Radio
Archived Dark Reading Radio
After a serious cybersecurity incident, everyone will be looking to you for answers -- but you’ll never have complete information and you’ll never have enough time. So in those heated moments, when a business is on the brink of collapse, how will you and the rest of the board room executives respond?