Vulnerabilities / Threats
01:37 PM

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
Threaded  |  Newest First  |  Oldest First
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
Current Issue
Five Emerging Security Threats - And What You Can Learn From Them
At Black Hat USA, researchers unveiled some nasty vulnerabilities. Is your organization ready?
Flash Poll
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
Published: 2015-10-15
The Direct Rendering Manager (DRM) subsystem in the Linux kernel through 4.x mishandles requests for Graphics Execution Manager (GEM) objects, which allows context-dependent attackers to cause a denial of service (memory consumption) via an application that processes graphics data, as demonstrated b...

Published: 2015-10-15
netstat in IBM AIX 5.3, 6.1, and 7.1 and VIOS 2.2.x, when a fibre channel adapter is used, allows local users to gain privileges via unspecified vectors.

Published: 2015-10-15
Cross-site request forgery (CSRF) vulnerability in eXtplorer before 2.1.8 allows remote attackers to hijack the authentication of arbitrary users for requests that execute PHP code.

Published: 2015-10-15
Directory traversal vulnerability in QNAP QTS before 4.1.4 build 0910 and 4.2.x before 4.2.0 RC2 build 0910, when AFP is enabled, allows remote attackers to read or write to arbitrary files by leveraging access to an OS X (1) user or (2) guest account.

Published: 2015-10-15
Cisco Application Policy Infrastructure Controller (APIC) 1.1j allows local users to gain privileges via vectors involving addition of an SSH key, aka Bug ID CSCuw46076.

Dark Reading Radio
Archived Dark Reading Radio
According to industry estimates, about a million new IT security jobs will be created in the next two years but there aren't enough skilled professionals to fill them. On top of that, there isn't necessarily a clear path to a career in security. Dark Reading Executive Editor Kelly Jackson Higgins hosts guests Carson Sweet, co-founder and CTO of CloudPassage, which published a shocking study of the security gap in top US undergrad computer science programs, and Rodney Petersen, head of NIST's new National Initiative for Cybersecurity Education.