 |
Featured Articles
|
|
|
 |
|
|
|
|
|
|
|
Current Articles
|
|
|
|
|
|
|
|
|
|
|
|
News Articles Archive
|
|
|
|
|
|
 |
|
|
|
| Storm Worm Dwarfs World's Top Supercomputers |
191 Views |
| posted on Monday, September 03, 2007 |
|
|
STORM WORM DWARFS WORLD'S TOP SUPERCOMPUTERS
By Brian Krebs
washingtonpost.com
August 31, 2007
Original Link
The network of compromised Microsoft Windows computers under the thumb of the criminals who control the Storm Worm has grown so huge that it now has more raw distributed computing power than all of the world's top supercomputers, security experts say.
Estimates on the number of machines infected by Storm range from one million to 10 million, depending upon which security sources you believe. But hardly anyone would argue that many thousands of new PCs are being stricken by the worm each day, largely because the worm authors are continuously changing their tactics to trick people into installing it.
Massive pools of virus or worm-infected PCs, known as "botnets," are principally used to blast out spam, host scam Web sites, or to flood targeted Web sites with so much junk traffic all at once that they simply crash and are rendered unreachable by legitimate visitors. But the criminals who control these infected machines could just as easily use them to do some serious number-crunching, the kind of computational analysis typically left to the world's fastest supercomputers.
IBM's BlueGene/L supercomputer.
In a posting today to a data security mailing list, Peter Gutmann, a computer science professor with the University of Auckland in New Zealand, said the Storm botnet could easily outperform IBM's BlueGene/L, currently the top-ranked supercomputer on the planet.
Gutmann's analysis assumes that the average infected PC is fueled by something close in processing power and memory to the class of machine used by the average computer gamer. Valve, the maker of the blockbusters CounterStrike and Half Life video games, says the typical machine has somewhere between a 2.3 to 3.3 GHz processor, with roughly 1 gigabyte worth of system RAM (system memory).
If we assume the average Storm worm victim machine falls within this range, the Storm cluster has the equivalent of one to 10 million 2.8 GHz Pentium 4 processors with one to 10 million petabytes worth of RAM. Whether we're talking about disk space or the size of a computer's temporary memory space, a petabyte is a truly staggering number. To put the size of a petabyte into perspective, Google, as of Aug. 2007, uses between 20 and 200 petabytes of disk space, according to Wikipedia.com. In comparison, Gutmann said, BlueGene/L currently contains 128,000 computer processor cores, and has a paltry 32 terabytes of RAM. A terabyte is about 1,000 times smaller than a petabyte.
In fact, Gutmann said, the Storm botnet has better hardware resources than the entire world's top 10 supercomputers <http://www.top500.org/>.
Even if you bring the average processing power or RAM down quite a bit, the numbers still favor the computational abilities of the Storm worm over the world's most powerful supercomputers.
Lawrence Baldwin, chief forensics officer for myNetWatchman.com and a researcher who closely monitors the spread of the Storm worm, said the sheer power of the Storm network is "scary."
"People aren't respecting the threat this thing represents," Baldwin said. "But when you pit it against the biggest military and government supercomputing resources, they're like a speck on the back of a fly compared to the power that's under the control of this one criminal group."
Baldwin said the raw power of the Storm botnet might be taken more seriously if it were more often used to take out large swaths of the Internet, or in attempting to crack some uber-complex type of encryption key used to secure electronic commerce transactions. "I'm sure there are other types of computationally intensive tasks that could be accomplished with a couple of millions of computers that would help the miscreants."
|
|
 |
|
|
|
|
|
|
|
............
In accordance with Title 17 U.S.C. Section 107, this material is distributed without profit to those who have expressed a prior interest in receiving the included information for research and educational purposes. Unless the information in question has been written and/or published by NHNE, NHNE has no affiliation whatsoever with the originator of this article. NHNE is, therefore, not endorsed or sponsored by the originator, nor does NHNE necessarily endorse, promote, or agree with the content. If you wish to use copyrighted material from this site for purposes of your own that go beyond 'fair use', you must obtain permission from the copyright owner.
|
|
|
|