Slashdot Mirror

RC5-64 is so solved, they are solving how to crack RC5-72.

RC5-72:http://www.distributed.net/rc5/

open4free (c) (tm) (R)

One of the other crypto distributed computing projects that's testing a higher level on encryption is only giving away $1,000 to the winner out of the $10,000 coming from RSA. Here's Distributed.net's cash distribution:
$1000 to the winner
$1000 to the winner's team (or to the winner if not on a team)
$6000 to a non-profit organization chosen by all participants
$2000 to distributed.net for building the network and supplying the code
And as ECC2-109 in being run by the company that owns the process, the costs of running the severs that support the project are not factored into the prize distrobution.

It seems that a better use of spare CPU cycles would be distributed.net's Optimal Golomb Ruler search, or Stanford University's Folding @ Home project.

Make an actual contribution to science - much more satisfying than looking for a very improbable E.T. or senselessly cracking encryption schemes.

Nooo. There is always Distributed or plethora of choices to occupy your CPU time.

What if the next version of WMA encryption were as secure as AES?

Umm.... Currently AES comes in 192 and 256 bit flavors and supports higher. But remember, they have to be sufficiently week such that a computer or (DVD-type) player can decode them on the fly. (That's the reason DVD's only have 40 bit encryption.) Given that they will have to have a single master key for everything. (DVD's have many master keys, knocking the 40bit down to something a few bits less. 36 maybe?) It would be possible for a group to simply brute force the key. Given that Distributed.net Has been doing this with RC5 implementations on many computers (i know how long it would take them in comparison, but computing power will catch up.) They could crack the master key in a couple years. Less if more people got involved, or if they made special hardware for it. Therefor, if they used that and enough people helped out, they could make it infeasable to use any encryption at all. Hell, it would probably take them a week at most to find every single DVD master key by brute force.

Sorry to hear about the theft. I can only imagine how awful it feels.

A similar but slightly less pie-in-the-sky thing would be to use the lab computers for batch processing during the night.

The Virginia Tech cluster having been in the news so much lately, I thought of another time at VT that we've had quite a cluster accidentially. Or, rather not accidentially. rdickert is a guy who was on the VT distributed.net RC5-64 team. His stats are here. At some point, he had installed the d.net client on almost all of the computers in the math emporium, and I think some in the CS labs. For those not familiar, the math emporium is an off-campus location owned by the university where people can come to use computers for various things. The computers there always have mathematica and matlab on them, among various other things. Anyway, when he was using them (~1998, scroll down on his stats), they were I think somewhere around 300 Mhz G-3's, and there were about 500 of them.

Yep. Eventually they figured it out, and shut it down, but wha'eva.

~Will

Check out Distributed Nets stat pages for a lowdown of what clients are running on what OS/CPU. This could offer a clue as to whats out there. :) http://stats.distributed.net/misc/platformlist.php ?project_id=25&view=tco

Distributed.net stats are BETTER than porn!

Well I'm not sure if it's any sort of relevant benchmark, but running the OGR benchmark of dnetc on the Ultra10 I used to use at work showed it could crunch gnodes *almost* as quickly as an AMD K6 500. I was surprised at that since it actually felt slower to use (the AMD setup was running Linux, BTW)...

Yes, but you have to go to an unusual step of decrypting.

You have to "decrypt" MP3 files with Winamp to be able to play them on PCM hardware too.

It differs from a compression scheme, since it has a secret key

A key of that length isn't very "secret". In practical, human-scale terms, CSS is no more "secret" than a Caesar cipher, as it takes no longer to decrypt a text than to copy an encrypted text.

it differs from a modulo add, since that is simply a different way of representing digits.

And CSS is "simply a different way of representing" data.

Watch somebody implement CSS as a stream cipher for one of the popular crypto APIs. Then it'd have a substantial non-circumventing use as required by 1201(b). In fact, any general-use program that brute-forces encryption keys has a substantial non-circumventing use, namely that of research into the strength of the cipher.

With negative dollar amounts? ]:3)>

I don't know what you are talking about!

There is now cow. . . .

Uh, someone forgot to tell United Devices.

The corporation is intimately tied to distributed.net and has been selling distributed / Grid computing to corporations for YEARS.

DOH! Shudda used preview button. Distributed.net.

Slashcode should auto-detect those screwups.

If I want games, I'll buy a gameboy. ]:3}>

Sorry Montgomery Burns, that would be a standard S.A.E. ton. I will try to be more clear in the future. ]:3}>

typical reporters fscked their facts in the story.

qoute "The first and easily the best known is SETI@home, which since 1999 has enlisted half a million people to analyse data from the Arecibo radio telescope in Puerto Rico, looking for signs of alien life."

I believe distributed.net's client was the first program of its type to download information from a remote server, use idle cpu cycles to calculate whatever, then resubmit it back to the central server. I ran distributed.net back in 98, more then a year before seti came out.

SETI@Home is the most popular project, measured by number of participants, but it was actually the third large-scale, public domain, distributed computing project. A lot of its functionality and design is based on the second project, distributed.net, which in turn is based on some design ideas from the first project, GIMPS.

SETI@Home has definitely done a lot to popularize distributed computing, and has influenced many later projects, including protein folding projects like Distributed Folding and Folding@Home.

To see what other projects are out there, take a look at my site about distributed computing projects. And click on the links to past years (on my main index page) to see just how fast this field of science is growing.

Kirk

P.S. Somebody please /. my site so I don't have to keep plugging it in these SETI@home discussions :-)

How many drones working P2P-style (you create these hashes, I'll create these ones) would it take to equal this supercomputer?

I believe that what you are refering to is called "distributed computing".

A good example of crypto-key cracking by distributed computing can be found here.

This would be an amazing idea if somebody hadn't already been doing it for the past six years.

Gee, that's a great idea. I wonder why nobody has thought of that.

Norton AV's flagging of dnetc is fully in error. The distributed.net staff is aware of the situation and is working with Norton to resove the issue.

A cow.

One has to wonder if DFBSD will die due to lack of following, or if it will be the next awesome BSD. I am currently running FreeBSD 4.8 Release on my workstation. It might be worth it to grab a spare machine and install it to see what's up. Only if the distributed.net client will work on it though. ]:3}>

How well do these blade boxes stand up to full trottle usage? Would a box like this handle running the distributed.net client for days and weeks and years? Although because this is an Intel box they will be slow as compared to AMD, but still a valid question.

How well do these blade boxes stand up to full trottle usage? Would a box like this handle running the distributed.net client for days and weeks and years? Although because this is an Intel box they will be slow as compared to AMD, but still a valid question.

How well do these blade boxes stand up to full trottle usage? Would a box like this handle running the distributed.net client for days and weeks and years? Although because this is an Intel box they will be slow as compared to AMD, but still a valid question.

Hmmmm:

PowerPC 970 G5 1800 rc572: 13,400,000.00

AMD Athlon64 1600 rc572: 5,771,251.00

Intel Pentium 4 3500 rc572 4,960,583.00

Hmmmm:

PowerPC 970 G5 1800 rc572: 13,400,000.00

AMD Athlon64 1600 rc572: 5,771,251.00

Intel Pentium 4 3500 rc572 4,960,583.00

Hmmmm:

PowerPC 970 G5 1800 rc572: 13,400,000.00

AMD Athlon64 1600 rc572: 5,771,251.00

Intel Pentium 4 3500 rc572 4,960,583.00

Hmmmm:

PowerPC 970 G5 1800 rc572: 13,400,000.00

AMD Athlon64 1600 rc572: 5,771,251.00

Intel Pentium 4 3500 rc572 4,960,583.00

Dosen't this patent cover applications such as distributed.net and other such distributed processing technologies?
IANAL, but wouldn't that count as prior art to this patent?

Most modern OS'es use HLT commands to power down inactive parts of the CPU. On such an OS, running a distributed worker like seti, folding, or dnet will make the chip run a little hotter, and probably draw an extra watt or two out of the power supply (depending on the chip and speed). On older OS'es it doesn't make a difference since the chip never really "idles" so to speak.

I'd say go for it. All processors die, but not all processors really live! ;)

Some relevant links:

dnet

folding@home - For this one, if you're on Windows, use the cmdline version. I've found the Windows version to be a little nasty and ALT+TAB you out of games that run full screen.

Seti@home

There's a thousand more, but those are the big ones. Have fun!

I've been using http://www.distributed.net/ on and off for a few years now and i've never had a problem with any of my processors. However I usually upgrade my cpu/mb every 3-4 years, so if you have or keep your systems longer i'd imagine any burnouts would be due to "just an old cpu" and not from the constant use. Then again I don't plan or expect my hardware to last forever.

As far as the power bill goes. I currently have a desktop, laptop, wireless router/hub and zaurus going the majority of the day - at least the systems are always on since I am too lazy to turn them off and have no need too. I also live with my girlfriend who runs the haridryer every morning and must have every light on in the house to check her makeup with. At the end of the month we get our power bill of $45-50 - which in my opinion is not a lot. We're also in California for the record.

check if distributed.net has an optimized athlon64 client, or help in writing one, and then compare yourself to other's stats.

they're going to do what distributed.net has already done, provide a client that can work on multiple projects, chosen by the user. Oh well, in this game I suppose it's really the size of your user base that matters.

I've been a big fan of distributed computing ever since distributed.net came out with their first client. The TCA Internet team used to be hot stuff back in the day as far as number crunchers (due primarily to me sticking the RC5 client on all three of the NOC's e450's as well as all the cube farm machines). So naturally, this interests me. I wanted to see what it took to get a grid-enabled machine. Costs involved. Scope of the project. The article's fine and all, but I knew I could go direct to the source. Not found. In fact, all of googles top 25 links to .ch sites seem to be down. Is this just me or did CERN disconnect their webserver and absorb the circuits into their grid or something?

I'll be happy if they include the barrel shifter, ROTL. I want to stay intel loyal, but it's hard when my ./dnetc speeds suffer so much. ]:3}>

I smell a distributed project!

Each client gets a block of pi, starts at the first digit, and attempts to play the next 9238472093847 bits as .mp3 (or any other media format) looking a coherant audio (or video) pattern. Move to bit 2. Rinse. Repeat. Profit!

Actually, a 1.25GHz G4 does 13Mkey/sec. Now, I think that is a dual processor score. So each processor is doing 6.5Mkeys/sec. 2.8*2MKeys/sec = 5.6MKeys/sec. So the newer G4s are actually more efficient (remarkable considering the bus multipliers involved).

ooops, yuo = own3d!!!!
http://n0cgi.distributed.net/speed/query.php?cputy pe=99&cpumhz=1000&recordid=1&contest=rc572&multi=0
Power PC 7450/7455 G4 1000 MacOS X 10.2 2.9005 RC5-72 10,594,666.00

adjust its length until its checksum matches that of "Oops, I did it again".

The people brute-forcing RC5 haven't even solved a 72-bit key yet; how do you expect anybody to solve a 128-bit MD5 hash?

It seems to me that more and more math problems are being approached in a brute-force, computerized way. While this is certainly a legitimate way of finding answers to a problem, aren't we missing the point of these problems by using it? It's not like anyone was really waiting on the answer to that problem. It's such a lazy disappointing answer to an exciting mathematical question: "Are there any magic knight tours on an 8x8 chessboard?" "Nah, I tried 'em all out, see." Are we seeing the death of "clever" mathematics where a simple elegant solution is found, correlating known theorems in novel ways that enhance our collective understanding of the way math works?

Now before you object, I am aware of really nifty, clever mathematical breakthroughs in recent memory. The recent polynomial-time primity test comes to mind. But what is the point of "research" and "inquiry" if we only care about the answers to the problem, and not the reason why? What is the point of finding the next Optimal Golomb Ruler" if we can't find a pattern relating one to the next? What would we really do with a magic knight's tour anyway, besides reading a clever and insightful proof of it's (non)existance?

Even a computerized proof would be interesting, if a method for proof-solving on computers were possible. And yes, it is possible to write proof-solving software that is at least as good as a human mathematician without upsetting Mr. Godel. But this brute-force type proofing is just plain dull!

Someone needs to convince those Japanese scientists to run this on their super computer.

There is also a direct trade-off between more general purpose systems and systems custom tailored to a task. Good examples are Deep Blue and Blue Gene. Both of these systems are designed with a particular task in mind (i.e. chess and protein folding) and therefor are able to leverage knowledge about the problem space to constrain the kind of hardware, the particular low-level instructions and the information flow within the system while achieving signifigantly greater performance on a small class of problems. I work with clusters that are used in scientific communities that have various researchers working on various problems. In these cases, the questions are about basic applicability of a particular problem to a particular architecture. For example a cluster with high-speed interconnects made of good COTS hardware will allow a user with a very granular problem to effectively use the cluster and it will also allow a user who needs the high speed interconnect because the problem space demands a high degree of internal communication. But the first researcher might also be able to make use of a grid of (for instance) many more computers with a total lower cost because (s)he doesn't need the high speed interconnect. The Earth Simulator gains a lot of performance (on a class of problems) because of the underlying vector processor architecture. Given the right internal bus it is conceivable that adding vector processor daughter boards to the next generation of COTS clusters could achieve similar results--but, of course, only for problem spaces that make efficient use of such processors and aren't bottlenecked by the communication requirements.

Real answers are always more complicated. For example: the equations needed for nuclear simulation will probably require dedicated hardware (as the need for protein folding has lead to Blue Gene) to achieve the results that the Pentagon needs. But for many super computing tasks, the flexibility of COTS clusters will still be compelling, especially for areas where the algorithms are not yet fully developed (e.g. brain simulation). An interesting keynote at OLS 2003 argued that (some of) the problems are not going to be the local computing power but the need to move large quantities of data between research labs across the world and combine computational systems using the 'grid.' (For a down home examples of problems that have been successfully tackled through course granular distribution just look at SETI@Home and Distributed.Net. So its not just the flops anymore...

i am in school, and so all my documents, reports and c++/java projects are on there.

I also have copies of my favorite software, aim 4.8 + aim+ (5.x doesn't play with aim+ well), the distributed.net client, putty, tightvnc, winamp, etc.

and thirdly, i carry a copy of my website, in case i need it, or other backup medians are not available.

Actually, with good algorithms, knowing the plaintext doesn't really help you. Witness the RC5-64 contest, where the plaintext was known, and with over 300,000 people working in parallel, it still took nearly 5 years!

However, the idea of keeping government supercomputers busy for weeks is a bit far-fetched. From what I understand, the NSA's "deep thought" supercomputer can crack an RC5 key in a few minutes. There's something to be said about a computer that needs 20,000 tons of coolant!

steve

i've always preferred the DNET client to the command-line S@H client. the data is broken into smaller blocks, and had built-in support for storing queues of data.
I certainly wouldn't call distributed.net "some little known distributed computing project"... it is quite well known throughout the computing community. while not as popular with the general non-geek public, a quick look at the stats pages at distributed.net will show many groups not normally associated with geekiness that are participating (albeit not as many as SETI...).
I don' think anyone is "spitting on SETI." People who have been running DNET since the beginning probably feel a sense of pride in their project, and feel some obvious animosity towards people who pulled their Idle CPU time from DNET and moved it to SETI.

The world needs no more than one computer, it's just very spread out.