Hardware acceleration of password recovery has been a hot topic for quite some time already. We were the first to adopt widely available graphic cards for this purpose and we’re proud of this. Today I’d like to share some thoughts on hardware acceleration for password recovery, its past, present, and future. I will also cover the most frequently asked questions regarding GPUs.
Posts Tagged ‘GPU’
We wrote about Cost-effective video cards recently, but what about better ones, if the prise does not really matter? Just read Best Of The Best: High-End Graphics Card Roundup at Tom’s Hardware. Large. Expensive. Power-consuming. But really fast — so best choice if you deal with GPU acceleration.
Btw, don’t forget to get a good coller for your new card — like this one.
Tom’s Hardware has tested two mainstream NVIDIA cards (GeForce 9600 GT and GeForce 9800 GTX) on several CUDA-enabled applications. The applications were:
- CyberLink PowerDirector
- Tsunami MPEG Encoder
- Super LoiLoScope
If you are going to purchase a new computer (or make it yourself), you should definitely think about graphics — for CAD/CAM, gaming, searching for extraterrestrial intelligence at home or password cracking. Of course, thinking of budget, too. I hope you’re already aware of NVIDIA SLI which allows to use multiple video cards, but how a single dual-GPU compares to two single-GPU ones? Read GeForce GTX 295 Vs. GTX 275 SLI: When Two Are Better Than One.
Note to PGP legal dept: I’m not going to put the ® sign every time when I mention PGP. I’m just tired; we already did that in our press release and on our web site, and I think it’s enough. No, really? Well, I’ll repeat one more time: all names like PGP are trademarks or registered trademarks of their respective owners in the UK, USA, Russia and probably somewhere else – e.g. in Albania. There are too many countries to mention, sorry :). Why should I care about (R)? Keep reading, and you’ll see the reason.
Note to PGP executive and marketing depts: thanks again for helping our marketing people to spread a word about company and our software. We have received many calls from local and international media, a nice press coverage, and a lot of people coming to our booth at InfoSecurity. Well, and several good orders – mostly from forensic/investigation people.
Now an update to my previous post. It becomes more and more funny: PGP has wrote about our ‘conflict’ in their own blog. And the author is… Jon Callas, CTO of PGP. He called his blog entry Lies, Damned Lies, and Marketing – not bad, eh? But the contents is even better. Jon starts with the words about ElcomSoft: “The company who made this has a great product, and as I said then, it’s a very cool product.” Thanks Jon, but we already knew that our software is “great” and “cool” – otherwise we would not get enough sales ;). But Jon’s story continues with the following:
[ElcomSoft] booth said, “the only way to break into PGP®.” This is a lie, and a lie in two directions.
1.They’re not breaking into PGP, they’re doing password cracking. There’s a difference.
2.They’re not the only people who do it. As I’ve said before there are plenty of other password crackers, both commercial and open source.
In short, the sign was factually incorrect, and lies about PGP.
If we lie, please sue us. If we don’t, better be quiet, please. But PGP marketing people have selected the 3rd way: complained to Reed Exhibitions and asked to destroy [a part of] our booth. Well done.
About : from my personal point of view, “breaking into PGP” can mean “password cracking” as well. Do we provide the tool to get access to password-protected PGP disk? Obviously we do. Did we say that it works in 100% cases, or that we cracked PGP encryption/algorithms? No we did not. Oh well, our English is definitely not perfect, but I think it is still better than your Russian, Jon 😉
About : yes, there is a lot of password crackers around. But I’m aware of just a single one (except ours, of course) for PGP Disk – and it is commercial; supports old versions of PGP Disk only; moreover, it is distributed only as a part of very expensive commerial e-discovery package – and it is MUCH slower than ours (because it does not use GPU acceleration). Sorry, I will not mention the vendor name here, simply because it is our competitor – and it did not pay us for an advertisement :). Jon, I’d appreciate if you can name the other ones (commercial or open-source). If you cannot, YOU lie. But I like your wording “as I’ve said before”; I think I should used it myself, too (e.g. “as I’ve said before, PGP is not secure and can be cracked” – without reference, for sure :)).
I recall how I talked to PGP representative a year ago – on previous InfoSecurity UK. The first question he asked was: “Have you received an e-mail from our legal department?”. I replied “Should I?”; he said “Yes”, and explained the reason: there was no (R) sign (near “PGP”) in our press release (Elcomsoft Distributed Password Recovery Unlocks PGP Protection). Well, see the note at the beginning of this post 😉
Another note: in fact, we were strictly prohibited (by Reed, but that’s definitely not their own initiative, but for sure PGP’s one) from printing anything about PGP on our booth. It’s a pity that I did not have a voice recorder handy. So if we wrote something like The only way to break PGP passwords, or The most cost-effective way to crack PGP passwords etc, such panel will be removed as well. We’ll probably try this next year. But we reserved the other place for InfoSecurity 2010 – not so close to PGP; I think it is a good idea anyway, because every half an hour they’re doing very loud (but not very smart) presentations telling people that PGP is #1 in this and that (nothing really interesting/technical/innovative).
Oh, I forgot to mention that we received a document from Reed explaining why they’ve removed our wall paper, finally – at the end of the first day, i.e. about 8 hours after removal. The official Regulations (sorry, I’m too lazy to scan it – but I will, if you wish) say that it should be done in advance (and no action can be made without prior notice in writing), but who cares? Anyway, for those who interested – here is how it looks like:
But I should also mention that Reed keeps their word: our panel has been replaced this morning (at their own cost). Have a look (the second panel from the right; the color is slightly different from the original one, but still better than nothing):
Lessons learned? You guess yourself. I would not say anything bad about PGP and/or Reed – they really helped us a lot. And I would NOT recommend PGP to send smarter people to the exhibition next year – so we’ll be able to save a significant part of our marketing budget 😉
After all… All of the above (as well as my other posts) is my personal view, and not an official position of ElcomSoft. Yeah, I’m the CEO of ElcomSoft, and I’m the person who approved the design of our booth (btw, only two days before the show: we were really busy doing technical stuff), but anyway.
And finally, thanks to all who made the comments to my previous post. As you can see, our blog is NOT MODERATED – in contrary to PGP’s one (which is actually premoderated, try it yourself; we made some comments there, but they have not appeared – at least in about two hours after writing). Censored? 😉
Last week a colleague of mine, Andrey Belenko, gave a speech at the Troopers conference in Munich. Olga wrote about it in this blog. All the talks at Troopers were awesome. Soon the videos and slide shows will be available for downloading on Troopers website.
If you have an opportunity, visit Andrey’s talk about green password recovery at Infosec, London. It’s on Wednesday, April 29th, at 15:20, at the Technical Theare. Also visit our booth K35 at Earls Court for free software trials.
There is only one way to break through PGP® encryption – GPU accelerated brute force – and that one is too many. New Elcomsoft Distributed Password Recovery v. 2.80.206 crunches PGP® passwords 200 times faster using graphic chips.
EDPR is all for cutting unnecessary costs, saving time and energy. Just using video cads you have at hand can result in excellent performance. In the graph you can see a huge leap in speed since graphic cards came into action.