Slashdot Mirror
NIST Studies Virus, DDoS Effect On Grids
Ben writes "Scientists at the National Institute of Standards and Technology (NIST) have launched a new campaign to study the effect of viruses and denial of services attacks on grid computing systems. Specifically, they're developing models to establish vulnerability and find ways of fixing problems. But a grid's very strength -- its distibuted nature -- makes it vulnerable, indeed, they're finding. (Via Science Blog)"
Hmm, I've never seen any serious computing grids that are open to outside networks or that run windows.
I think its common wisdom to isolate grids from the internet and other potentially hostile networks.
But a grid's very strength -- its distibuted nature -- makes it vulnerable, indeed, they're finding.
Ewwww, awkward!
Better: But the grid's very strength, its distributed nature, makes it more vulnerable to these types of attacks.
Or: However, they're finding the grid's strength -- its distributed nature -- makes it vulnerable.
This is one of those times dramatizing a sentence makes it worse.
Cue in jokes about studying the slashdot effect on grid computer...
But seriously, what can simulate a DDoS more accurately than a bazillion slashdotters trying to RTFA and get the slashdot fix?
Did anyone else read that as "NIST Studies Virus, DDoS Effect on Girls?"
I suppose DDoS'ing a girl is a pretty good way to give her a virus.
Slashdot is proof that Sturgeon's Law applies to mankind.
http://www.nist.gov/public_affairs/techbeat/tb2004 _0730.htm#tackling
Does anyone know anything about the scienceblog.com site? It doesnt seem very reputable considering all the ads and the very obvious SEO technquies (look for the hidden links at the bottom).
In America we are imprisoned by our fear of them.
one of the disadvantages is that the same data will be sent to multiple computers. You can see that they used a grid computing system to create the article:
From the first paragraph:
Grid computing takes advantage of ''down time'' when computers are not using their full processing power to provide quick answers to problems in fields such as genomics, engineering design and financial services. While parallel processing typically involves tying together multiple computers at a single site--all using one piece of software--a computer grid may be much more geographically dispersed, composed of many heterogeneous computers whose availability may change over time.
The third paragraph:
Grid computing takes advantage of ''down time'' when computers are not using their full processing power to provide quick answers to problems in fields such as genomics, engineering design and financial services. While parallel processing typically involves tying together multiple computers at a single site--all using one piece of software--a computer grid may be much more geographically dispersed, composed of many heterogeneous computers whose availability may change over time.
Crushing dreams at the speed of sarcasm
The perfect web ad for the slashdot crowd!
Kind of a waste because it has exactly the same text as scienceblog. same text as the scienecblog.
Friends don't help friends install M$ junk.
I think its common wisdom to isolate grids from the internet and other potentially hostile networks.
So you want to build a third internet? Sounds great, so long as you let me into internet 2, which was built specifically for grid computing on university sites. When you migrate to internet 3, will you promise to keep it windoze free as a demonstration? Sooner or later people might understand how insecure commercial junk degrades a network.
Friends don't help friends install M$ junk.
Grid computing takes advantage of ''down time'' when computers are not using their full processing power to provide quick answers to problems in fields such as genomics, engineering design and financial services.
The way I understand it, they're talking about all the cubies in Charles-Schwab and Raython and Citibank, with Folding@Home and Seti clients running as screensavers. Not dedicated clusters; just plain old ordinary workstations.
And I'd imagine the viruii and worms and DNS outtages all take a serious bite out of their collective assets...
Informative.
A GRID is a non-centralized distributed system, sharing storage, processing and connectivity with quality of service guarantees, over open protocolls. Is that about right?
Last summer, I was in Barcelona for a class trip. We visited the European Center for Parallellism of Barcelona (Like there are redundant arrays of Barcelonas. Well, there's the smaller town/city of Badelona right outside Barcelona.)
Anyway...
The CEPBA is a partnership with IBM. I talked to one of the IBM researchers there. They very much believed in the GRID as a distributed system that would hold all your personal data for you, and where you would buy your processsing power and storage from big vendors. Thus users wouldn't have to keep up with the hardware advances themselves.
I suggested that some of the less time-critical processing and storage resources could be provided by the nodes themselves. He did not buy into this idea.
This philosophy reminds me of the old time-sharing systems of yore. If GRIDs are really deployed to a vast number of users, I would predict that users with smaller processing power would team up and sell their (lower quality?) processing to other users, much as the F***** Article says. The only thing that could preclude this would be an enforced requirement that only reputable vendors provide services with QoS guarantees, and digital restrictions stop users from selling their cycles.
Why not have several layers/levels of quality and security? That's much of the point of QuS, isn't it -- telling what's your worst offer and the client deciding beforehand wether to accept your service level?
Oh, look: Now their saying that institutions really WILL be able to pool their resources What is GRID compiting
Looks like I was "getting with the program" better than that IBM guy was. Either he misunderstood or given wrong information (something I've done a few times and been ashamed of), or is a firm believer in that Those darn kids will never provide the computing power! Only me and my VAX!
Irene KHAAAAAAN!
This hypothesis seems to go against logic but maybe it holds some water until things change a little. When you have one very good point of control to access to the system where is the difference then? Also when distributed systems use multiple locations as well as multiple configurations doesn't this create a more survivable system? The laws of nature clearly say that biodiversity is directly linked to an ecosystem's success. An attack or technical problem can not effect every part of a diverse system in the same way. Lately I have been comparing the laws of nature to the laws of technology and I have come to he simple conclusion that since computer systems are governed by the same laws it is inherent that the laws apply equally to there functioning parameters and design. This area of convergence between the laws of nature and computing is to interesting to ignore. Software could be developed by writing an ancestor program and creating random variations that are 'naturally selected' by simulated use and disruption of the population of software being tested, evolving software basically.
411 Y0UR 8453 4R3 8310NG 70 U5!! -NSA
I've always just likened a grid to one big computer composed of many parts, which makes the next bit easier to visualise.
As a grid basically has all the connected boxes on the same framework, the possible attacks could either be external or internal to the grid. If external then it's either the fault of the underlying OS or the grid itself and should of course be repaired. Just like a single computer.
However I think it's unlikely that internal infection could occur (which is how most networks get infected) as for one the virus has to be written especially to take advantage of the grid, i.e. no script kiddies, secondly infecting the grid would infect your own box as it is part of the grid. Just like a single computer.
Also because the of the way resource allocation and processes move in grids like globus it'll localise the infection first, so if anything your box would get most of the infection and then only start trickling outwards.
But they're finding a grid's very strength -- its distributed nature -- makes it vulnerable, indeed.
This is more fun than the Soul Train Scramble Board!