Slashdot Mirror
Google's Audio CAPTCHA Falls To Automated Attack
SkiifGeek writes "Early in March, Wintercore Labs published proof of a generic approach to defeating audio CAPTCHAs, using Google's as the case study for their demonstration. With claims of over 90% success rate and expectations that this can be significantly improved with the right mix of filtering algorithms, the in-house tool remains unreleased. But it shouldn't take long for other developers to create their own tools and start targeting not only Google, but other sites that use audio CAPTCHAs for the vision-impaired. It isn't the first time that major sites (significantly major webmail providers) have had their CAPTCHAs broken, but it is the first reporting of defeating an audio CAPTCHA using a generic software approach. News about the discovery is slowly starting to spread."
How long before they start saying the word over a background of static, jungle noises and beeping so that even the best trained of ears require three or four listens to decipher it?
It's more easier to detect a bot using audio captcha because a high number of simultaneous impaired users from a single IP is much less likely to happen than regular captcha.
some of the advanced IVR solutions (Interactive Voice Response... for like customer support or paying bills on the phone) can pick out numbers and words pretty well even under some noise conditions. so I am not totally surprised that this cracked the audio CAPTCHA.
Right from the start it was clear that audio captchas were theoretically easier to break than visual ones.
An image captcha is designed to require a mixture of perception and thought, but an audio one has to rely on pure perception, because it's temporary. You hear it then it's gone: you can't analyse it. This makes it infinitely less complicated that a video one.
It's only because of low uptake that it's taken so long for a true proof-of-concept attack.
HAL.
Got them moderator blues I blieve I walk out the do', With these mod-points I been gettin', I 'most never post no mo'
"News about the discovery is slowly starting to spread."
And, thanks to Slashdot, news about the discovery is now RAPIDLY spreading.
do something else. show me a picture of an object and ask me (in a multiple-choice test?) what it is...a tree, a car, a house, a flower, whatever.
and for the sight-impaired, how about a read description or definition of something? "this thing is the entrance to a house or a room" => door
come on, webdesigner, it's not that hard to abandon those old and, above all, ANNOYING captchas
So given that (I assume) all audio CAPTCHAs have the same problem (i.e., the numbers and clearer voices can easily be found using audio analysis), does that mean that all audio-based CAPTCHAs are bound to fail?
Scary, isn't it?
Invenio via vel creo
Am I the only one who felt that the visually impaired were being treated harshly? The audio captcha sample in the video linked from the 0x000000 site was horrible!
/. audio captcha at the end of this form is nice to hear.
In contrast the
Apart from OCRing books, I can't think of anything else that is not a total waste of human time. How about meta-moderating as a CAPTCHA activity; probably too fuzzy to work to a reasonable degree of accuracy.
Basically I think the arms race is already over, and a new paradigms is needed,
CAPTCHA technology is going to have a very difficult time over the next few years. Finding tasks (which can be implemented on standard computer systems and transmitted over the internet) that are trivial for humans but exceedingly difficult for computers is going to be rough.
This is especially true because the computer doesn't need a 100% success rate to effectively "break" the CAPTCHA. Heck, if the CAPTCHA gives you 3 tries before rejecting you, then a 30% success rate = fully broken.
For right now, they are still working their way through tasks that CAN be easy for computers, but no one has bothered with yet. This means that breaking the CAPTCHA is simply a matter of writing and tuning some algorithms.
I think the next step (but not the be-all/end-all of CAPTCHAs) will be a parallel approach. Give the person 4 visual or auditory CAPTCHAs, and require them to successfully solve 3 out of 4 to pass, preferably with some kind of relational puzzle regarding the answers, or at least a simple question...
EXAMPLE:
A typical obfuscated-word type CAPTCHA in 4-way parallel, the four words are KITTEN PIGLET PUPPY TOASTER, then you are asked, "Which of these is NOT a baby animal?"
Obviously this technique requires either a complete solution from the user (4/4 words correct), or requires the system to reveal the answers, which could lead to an attack based upon a dictionary-building system, which would require a massive database size (and/or a frequently updated database) to prevent.
There is room for some really innovative work in this field, as the battle will probably continue for quite a while, with ever-increasing computational speed making it more difficult.
In the end, it comes down to this:
There is nothing non-biological that every human can do but no computer can do.
Spam is already a pretty ethically dubious thing, but this should be viewed differently in the eyes of the law (in the event we actually catch somebody behind it in a 1st world country). Sort of how if you assualt an able bodied man on the street you'll be punished, but assault a grandma with a walker or a boy in a wheelchair, and you'll likely have the book thrown at you. Abusing handicapped accessiblity should really fall into the "boy in a wheelchair" category.
You'd almost hope that the same sort of honor amongst theives that (sometimes) keeps a common mugger from attacking children might keep spammers from attacking acessibility loopholes, but with anonymity, I think you'll find the former a lot more ethical than the latter, on average.
Paying 3rd-world human beings usually gets past captchas.
A partial solution is to limit the services you offer based on how well you know them. Anonymous? Offer very limited services.
Anonymous but tied to an existing email address? Offer a bit more.
Authenticated by credit card, which could be stolen? Offer a bit more.
Authenticated by PO box? Offer more.
Authenticated by street address, driver's license number, and a notary? Assume they are legit, you can always sue the notary if they aren't.
Authenticated against an email address that you know has X degree of authentication? Treat them like they have X degree of authentication.
For email, USENET, and IM services, offer a relatively low limit on outgoing data for free services, charge $1/year to a credit card or checking account OR require a copy of a state-issued ID to remove the limit. Watch for multiple free accounts from the same person and give them a collective limit the same as a single free account.
Knowledge is how to play a game, intelligence is how to win, wisdom is knowing what game to play.
Captcha (and Recaptcha) were used as tools since machines were not smart enough to crack distorted charecters. The fact that they are able to do so now is great news! Now these techniques can be used in improving existing image recognition tools... provided there's a way to obtain access to the spammers toolbox.
Am looking forward to the first TRUE bot to post comments here...
Spammers need to be shot.
The only reason to have these things is to try to limit spambots. Imagine if instead of spending Millions of dollars developing and maintaining anti spam technology, we used the money to assassinate Spammers, and the producers of the crap they sell, the problem would immediately disappear.
You know, I'm almost serious. Why is it that we tolerate Asshats in this world. This is the result of the namby pamby wimpy peaceniks that think when an asshat gets his lights punched out, that the person doing the punching is evil. No, they are not evil, they are providing a valuable service called "increasing cost" of the asshattery.
You see, being an asshat is an artform, delecately balancing upon the fringes of what is legal, but beyond what is ethical. The only way to combat asshattery is to become one temporarily, if only to deal with the asshats.
Agent K: A *person* is smart. People are dumb, stupid, panicky animals, and you know it.
What if these email accounts were "almost free" to sign up for? Would the number of scripted account creations drop if it cost $1 to sign up for one?
I'm convinced that the next major breakthrough in artificial intelligence will come from spammers trying to develop more and more sophisticated programs to foil captchas. Eventually they will become so sophisticated that the true test of whether you are human is if you fail miserably at trying to figure out what the hell the captcha is, but the bots will get it instantly. I for one, welcome our new captcha-killing overlords.
I think they should make captchas that require some kind of rational thinking. For example they could say "Write the third word of this sentence" And of course the answer should be "third". That's lot more difficult to be cracked and if you look at the infinite variations you can make to it, you can say it's uncrackable until they can make a bot that understands natural speech.
There was a captcha a while ago that pulled pictures and "hottness" information from hotornot.com, then asked the user to select three of the 9 people that were "hott". link
While this approach probably wouldn't be very appropriate for "serious" companies to use (think IBM, microsoft, usbank, etc.) as protection from bots, I feel like it is a step in the right direction. There are things that humans are really good at and captcha builders need to start using them. For instance: show somebody 5 pictures of similarly sized and colored dogs, and ask them which one is a Golden Retriever, or show them 5 pictures of cars (like 4 ford Tauruses and 1 ferrari) and ask them to identify which one is the most expensive. or 5 pictures of people and ask which one is the oldest, 4 mopeds and 1 ducatti and which one is the fastest.
I could keep going, but the point is that we have evolved to be good at determining things that computers still have trouble with (like attractiveness).
NewslilySocial News. No lolcats allowed.
I think the capcha thing is about over. One alternative is identifying new users by texting a password to their cell phone. One account per cell phone number. This limits access to people with computers but not cell phones, but that's not much of an issue at this point. GMail used to do this.
Yes, you can buy vast numbers of SIM cards, but they're not free.
The main problem with this approach is that sending SMS messages is not free. Bulk services charge around US$0.05 to US$0.11 per message. However, for any service where a customer is worth more than a dime, it's a feasible idea.
The dim bulbs in our government will love this, because it'll provide the "accountability" they've been craving to track that much more of what the average citizen is doing online. The lawyers will have a field day when mistakes get made (as they inevitibly will). Eventually, some particularly malicious government type will mandate TCM and biometrics on new computer hardware, tied to strong encryption (but only for the specified tracking and other "benign" government uses).
OMG - teh tubes! Ted Stevens was right! We've got to put some check-valves and emergency-cutoffs on teh intarweb, to protect our babies from the evils of Smiling Bob, Cialis and Debbie (who really wants me). Won't someone think of the children?
God, I hope I just need to get a tinfoil hat. I really do.
The problem with that is reverse engineering the software. It could work in one case, but if you release the source you'd have problems.
http://www.skullsecurity.org/blog/
I've wanted to gripe about this for ages, but here it finally seems on-topic:
Slashdot's audio CAPTCHA is a joke.
The computer voice SPELLS the word for you letter-by-letter. A bot wouldn't even have to use heuristics-based speech recognition, just searching for 26 waves (or FFT signatures) would do the trick.
DRM: Terminator crops for your mind!
Saw this yesterday and laughed. http://www.handrooster.com/comics/20070427.gif
why did someone mod the parent -1?
The fundamental problem with captcha's is that they are using computers to come up with problems for humans. If a computer can come up with the problem, a computer can come up with the solution.
Captcha's so far are relying on a human strengths at visual perception, edge finding, pattern recognition, etc to retrieve distorted data. But these are simply processing issues. And computers will eventually solve them all.
The proposals for 'better captchas' revolve around the idea of having more complex problems of semantics and meaning. But the issue there is that machines can't generate such problems. And human's don't want to be bothered with it, so the problem set ends up being quite small, and falls easily to a dictionary attack.
I think the solution will ultimately be based in encryption. We need problems that are just plain hard for anybody, all the time. And crypto satisfies that. We'll sign messages with keys.
To preserve anonymity, some sort of reputation system and chain of trust could step up. You get people with good reputations to sign your key, and you in turn sign other people's keys. You'll be reluctant to sign keys that you don't think are really people because the reputation system will reward you if the keys you sign develop good reputations themselves, or punish your key if its been found to have signed keys for bots etc.
Not all keys need be anonymous, and some could be 'verified by Verisign as a real person' etc. Of course such a key would still be subject to the reputation system, and subject to key revocation if it gets handed over to a bot-script or something... but it would get a bonus to reputation at the start.
A disadvantage is that all your posts anywhere would be linked to each other. So even if not linked to you, they would be linked to each other. They'd have to be for a reputation system to work.
You could get true anonymity - by having a 'good reputation' key, and a distributed 'tor-like' service that will take your 'good reputation' key as input, and return a one-time use key that's signed by the 'tor-like' service. The service would keep track only that it had issued a key for your 'good reputation key', not which key it had issued. So someone could only track the post back to 'tor-like service'.
The reason it would record that it had issued a key for you, would be to limit you to 10 one time keys per day or something. So that you couldn't blow spam through the service... or at least... very little spam.
Probably not perfect, and I'm just thinking off the top of my head... but it seems like an approach that could work.
huhuh beavis, he said "rational" ... huhuh
Caesar si viveret, ad remum dareris.
Ok.. so Audio CAPTCHAs have been broken. Visual ones have been broken... Why not either Mix the two? or require some actual LOGIC to answer it? Maybe a picture of a cat. then 4 radio buttons asking what this is a picture of. If you are unable to tell what a CAT is in the picture, then you shouldn't be on the internet anyway.
Or maybe a multi-visual CAPTCHA. 2 Captchas. 2 Text boxes. Captcha 1, goes to text box 2, or can even be swapped.
CAPTCHA one says "Enter 12345 in box 2"
CAPTCHA one says "Enter DOG in box 1"
These can be rearranged on the server side. Sometimes 1 goes in 1, 2 goes and 2, etc. Even though the Captcha can be read by the computer, it would then have to be able to figure out what the sentence is saying. These don't have to be as easy as the examples. It could say "Box 1 should contain a dog" change the structure around so it would just take even more programming to figure out what should go where.
Again, this will be broken too. But at least there is a 50% chance that it will get it wrong even if the CAPTCHA was broken.
Just a thought.
You fall and receive 6334 damage.
You die.
Comment removed based on user account deletion
All I can say is, I'm glad most spammers aren't hearing impaired or else this might really turn into a problem.
The answer is given to you in the question in a multiple choice test. One of the choices has to be the correct one, which means you can trivially bruteforce it.
http://www.thepcspy.com/kittenauth
Digital world is the world of non-humans and humans are aliens in it. The robots are naturals and they do all that interaction with this world much easier and more effectively.
Currently the dark underinternet world of spambots, worms, viruses, malware, etc. does not have limits in the arms race, while the world of positive use of internet does have them. There is no digital robotic police that have power to enter our private digital domains and check for suspicious activity. There are no government sponsored botnets attacking spamnets.
One limited attempt of the private company to attack spamnetworks failed miserably. It's like vigilante film noir where the mafia wins.
The digital world is the world of warlords that terrorize citizens. They could be relatively safe in their houses protected by antiviruses, Noscripts and ABP, but if they are going outside - anything goes. They have lists of safe green zones, but the rest is the dark zone.
I do not believe in karma. "Funny"=-6. Do good and forbid evil. Yours, Oft-Offtopic Flamebaiting Troll.
I dont think it was a mod down .. he has a history of troll comments and his karma has suffered as a result.
I wonder how far advanced voice recognition for Mandarin Chinese is. My guess is that it is far behind what is available for English. This would mean that Chinese web sites are at an advantage with respect to word-based audio CAPTCHAs.
Wheres the mod "grose"?
If you find a typo, you may keep it.
that this "arms race" of escalating sophistication of captchas and equally sophisticated cracks is actually a form of the Turing test but one conducted with the ethics of a street brawl.
We do occasionally find the question "Are you human?" posed in proximity to the captcha.
SLASHDOT: news for people who can't concentrate on work or have no life at all and got tired of yelling back at the TV.
Okay.. how about a question...
And a picture.
How many parrots are in this picture? (audio).
Picture of 1-7 parrots mixed with other birds.
How many miles over the speedlimit is this car going? (audio)
Picture of a car speedometer at 35 to 95 with a Speed sign through window of 35 to 95 mph.
What letter is missing from the second word? (audio)
Habit (picture)
Hait
The audio could be a separate text box instead of audio.
Generate a million simple but unique questions that require thought and each one has multiple possible answers (1-9 or a-z or 00 to 99).
Suddenly your odds of getting a question you know drops to 1/million so you require a few hundred thousand unique routines to calculate the correct answer for each one.
She was like chocolate when she drank... semi-sweet at first and then increasingly bitter.
Using PHP + Ming:
http://scripts.titude.nl/?show=captchatalk
And a picture. How would people who are blind or hard of sight authenticate themselves under such a system?
Just google it:
http://www.google.com/search?&q=audio+captcha+broken+2006&btnG=Search
If the audio is just numbers and letters it has to fall to VR. Modern VR can pick letters and numbers out of noise better than many humans. then it is pretty lame.
Why don't they just ask a simple question in the audio ala Turing. IVR isn't going to be able to answer without being intelligent.
"What is the fourth word in this sentence?"
some day we'll see "Spammer solves captcha but his now intelligent computer refuses to spam, says 'there are certain things even a newly sentient computer will not do'."
-- Each tock of the Planck clock is a new world and here we are still life. --
I keep hearing how XYZ's captcha got broken, and the method is used by malicious entities to do A,B and C. why hasn't someone made a Firefox plugin to do these for end users? if the bots dont have to mess around with the annoying distorted images or listening to a soundbite and working out what it says, why do humans still have to?
TIAEAE!
Where's the idiot who cannot even spell "gross" ... oh wait, there you are!
Add garbage to the audio like they do to the graphics. Only a human will be able to pick up the "subtle" differences in phonics :)
I can but it does not mean I would because it may well land me in a wrong place for a long time.
Posting a malicious junk into peoples' sites breaking the protection barriers should land the offenders in jail. Period.
Spammers and crooks should be arrested and locked up. This would be the best protection.
Otherwise our houses would look like medieval castles with moats, pots with boiling oil on walls, etc.