Personal tools
You are here: Home Blog The Cleversafe Idea
Document Actions

The Cleversafe Idea

“How did you get the initial idea for Cleversafe?” is a question I am asked fairly often possibly since I don’t have a long career background in data storage systems or in coding algorithms. What lead me to that idea of building a geographically distributed Dispersed Storage grids was that I was looking for a way to store my personal data and I had been reading a lot about the history of cryptography.

Prior to Cleversafe, I started a company called MusicNow which was a leading business-to-business provider of (legal) digital music services.  We built and operated download stores, music subscription services and Internet radio services which were sold by companies including, Best Buy, Microsoft and Earthlink.  In April, 2004 we sold MusicNow to Circuit City (who since sold it to AOL who then sold most of it to Napster).  After the Circuit City acquisition, I took the summer and fall of 2004 off which was the first time in my adult life that I hadn’t worked.  One of my projects was to organize all my stuff, so I digitized and organized all my financial records, pictures, correspondence, etc. which took several weeks. 

I ended up with 30 GB of data which I needed to store for the rest of my life since I knew that I would never again want to spend so much time going through that organization process.  At MusicNow, we had built a system to store all the music in the world, so I was quite familiar with the state of the art in digital storage.  I needed a cost-effective system that could store my data for the next 50 years and knew that existing storage methods could not meet those requirements.

In 2004, I was also reading a lot about the history or cryptography.  In particular, I was reading a lot about Operation Fortitude:  how the Allies in WWII we able to have the Nazis initially believe that the landings at Normany were just a diversion.  It was the most ingenious setup I’ve ever heard of – and it worked!  (For those interested in a fascinating and very detailed read in this area, I highly recommend Fortitude: The D-Day Deception Campaign by Roger Hesketh.) 

Inspired by the historical richness of cryptography, I moved on to directly explore cryptographic techniques and code breaking methods which lead me to read Code Breaking: A History and Explanation by Rudolph Kippenhahn.  As I was reading Code Breaking, I took the time to “do the homework exercises” which meant that when the book covered how to break a monoalphabetic substitution cipher, I took the time to break a couple monoalphabetic substitutions as well as many other forms of ciphers.  In doing these exercises, I learned a lot about how to use pieces of coded information to derive original data.

Reading about counter-intelligence and code breaking was not a part of a master plan to start a new business; I was just following my personal interests.  But when I later started to think about how to build a system to store my personal data for 50 years, I had a good foundation in the mathematical techniques for coding and decoding information.  With that foundation, I immediately had the strong intuition that you could create a system with the characteristics now found in Dispersed Storage.  And so following that intuition, I wrote a very early prototype which was the first step in creating Cleversafe.


 

Chris

Operation Fortitude

Chris,

That is interesting how operation fortitude was part of your inspiration; I was wondering did that book mention the imaginary man? ( http://www.damninteresting.com/?p=176 ). I found amazing the level of detail the British went to in inventing an entire persona as part of the misinformation campaign.

Jason
Posted by jresch | Oct 16, 2007 02:26 AM

The Imagionary Man and Fortitude

Jason,

The book Fortitude by Roger Hesketh doesn't go into detail on the imagionary man -- a facinating story in itself for sure. Fortitude is more about the counter intelligence programs that the British ran in WWII. In particular, it is about how the British turned all the German spies in Britian so the British ended up running Germany's spy network in Britian. Remarkable, but true and really great reading.

Chris
Posted by cgladwin | Oct 16, 2007 02:30 PM

A variation on Dispersed Storage

Thanks Chris for the background on Cleversafe and some insight into your personal life. I hope you don't mind but I thought I
might post an idea for a variation on Dispersed Storage.

Imagine that you have data to protect that is of the highest possible national security value to a nation like the US,
Russia, or China. You store it on a Dispersed network, and take the utmost precautions to utilize the strongest possible
cryptography. In addition, each silo is located in a hidden government location or military base, and each location is 'hardened', built below ground, utilizing steel reinforced concrete, etc., designed to survive near hit nuclear strike (it is not really possible to design something to withstand direct nuclear strike). Given all these precautions, it is reasonable to assume that enough silos will always survive to retrieve the data even in the event of nuclear conflict.

However, an aggressive opposition government could conceivably learn or determine the locations of these silos, and instead
of trying to destroy these silos, render each one temporarily 'incommunicado', via a combination of EMP attacks, chaff attacks to foil microwave technology, and destruction of land lines and sub surface lines via surface bombardment with
conventional or nuclear explosives, or via sabotage. In this scenario, your dispersed data is not destroyed, but the nodes cannot communicate sufficiently to reconstruct the data, for a period of say, an hour. This could be enough time for the opponent to effect an attack which the denial of your dispersed data renders you vulnerable to.

The solution? Mirror that data on another dispersed net, with each silo located on a submarine at sea. This creates a dispersed net with undetectable, highly mobile underwater silos, some of which might be under arctic ice, in the south
Pacific, or located in inland lakes (i.e., truly 'dispersed'), which the opponent has virtually no chance of ever determining
the location of. In the event that the land based dispersed net were unavailable, there is a very high degree of probability that enough of, if not all of, the backup 'at sea silos' would be available to retrieve the data. Technology exists that enables underwater platforms to send and receive 'radio' type communications without surfacing, so the retrieval of the data would likely not even be detected by the opponent.

This scenario offers significant hurdles, primarily maintaining a fleet of serviceable submarines of sufficient
sophistication to accomplish this mission. But to a government like the US, China, or Russia, such a monetary cost would be trivial compared to the denial of, say, nuclear launch codes or classified encryption key material.

Thanks again for letting me express an idea here. I didn't realize this would be this long when I started typing it :)

John
Posted by jbitten | Oct 17, 2007 12:27 AM

Submarine Storage

I think that's an ingenious idea, the submarine fleet was designed to survive a first strike nuclear attack to preserve a deterrent effect. One note to keep in mind though with underwater radio is that it's extremely low frequency ( http://en.wikipedia.org/wiki/Extremely_low_frequency ) and only capable of transmitting a few characters per minute, it is also only one way (to the submarine), so writing to a dispersed (and submersed) grid would be slow and impractical for very large files. (There of course may be classified technology that allows for higher bitrates) When reading, an ELF signal could be used to tell the "submersed grid" to raise their antennae to the surface where they can communicate the slices back through satellites. It would have a high start up latency, but its capable of surviving just about any imaginable catastrophe.

Perhaps a more humanitarian purpose would be for the dispersed sub net to store a backup of useful human knowledge, (wikipedia, classic books, MIT's online course materials, perhaps even an archive of the Internet) which would prevent humanity from slipping into a dark age following the destruction of most information which is now stored on EMP-vulnerable computers.

Jason
Posted by jresch | Oct 17, 2007 11:45 AM

Information Dispersal at the Movies

John,

First let me say that I don't have a security clearance and don't know for sure how organizations like the US government implements its security. But I would speculare that governments and defense organizations have been using information dispersal methods to secure things like weapons launch codes and cryptographic keys for decades.

When you watch an old submarine movie, you'll often have a scene where two officers have to both turn weapons launch keys at the same time. So if hollywood was already making a mechanical equivalent of information dispersal a cliche in the 50's, then I would certainly expect that governments and military organizations turned to information dispersal long ago. And it is very interesting to consider what kinds of systems have been put in place in confidential environments.

Chris
Posted by cgladwin | Oct 18, 2007 12:27 AM

another perspective...

First, Chris, I enjoyed the background behind Cleversafe. I am convinced that all the best ideas emerge when we're not looking for them.

John, your concept is interesting, but I think it misses the bigger picture. Should the situation on this planet escalate to the point of large-scale nuclear conflict, the survival of government secrets will be all but irrelevant, except, perhaps, to future interplanetary archeologists studying the remains of our species.

And for those who might manage to survive such a conflict - including the men and women at sea in your subs, those in regions distant from the conflict, and those who managed to find suitable protection before a strike - one would hope they learn a valuable lesson from the outcome. They'll need all the resources and cooperation they can muster to stay alive. I'm confident that data protection will not be on their list of priorities.
Posted by joseph martins | Dec 13, 2007 12:48 PM
Weblog Authors

cgladwin

Location: Cleversafe Chicago
cgladwin
Chris Gladwin wrote the first Dispersed Storage prototype and is the Founder, President and CEO of Cleversafe, a company commercializing this technology.

jbellanca

Location: Chicago
jbellanca
Cleversafe founder. MIT Graduate, history of working for technology startups. Areas of expertise: product design, interaction design, requirements.

rkennedy

Location: Chicago
rkennedy
VP of Product Management and Strategic Alliances for Cleversafe. Responsible for product management and product marketing and ensuring product roadmap and features meet the demands of the marketplace