Slashdot Mirror
Turing Tests to Stop Spam
cexy writes "The Register has a story about how Hotmail and Yahoo! are using Carnegie Mellon developed captcha technology (completely automated public Turing tests to tell computers and humans apart) to stop spammers from automating signups for accounts from which they can send spam. These guys are using captcha too, but to stop incoming spam."
my Spam filter in Yahoo catches way, way, more than the one at hotmail. It is always surprising to me when you open a new hotmail account that it takes only like a week to be flooded with Spam. A week of doing nothing with the account but initially opening it. *sigh*
that is why. all the spammers are targetting hotmail. I hate the anti-ms bias. I use a filter on my hotmail. It is an allow only filter. Those are the best kind because I make the decision of who gets through to me.
For those who dont know, The CMU developed captcha project is great. Check out their work here:
http://www.captcha.net/
Does Hotmail really think that I have friends named things like ilikeitinthebutt?
I've only had my Yahoo account since last year and my Hotmail account since 1997, so this may not be a fair comparison:
Yahoo spam today:
0
Hotmail spam today:
18
Which is doing a better job at stopping spam you say?
Saskboy's blog is good. 9 out of 10 dentists agree.
I would rather Yahoo stop spam from getting to my mail acocunt before they concentrate on stopping people from signing up automatically. I'm one of the few people who actually pay for Yahoo "additional" services. I thought I would get better anti-spam support. Not so far. I literally have 10 to 20 an hour and I can't block anymore because Yahoo only allows 100 addressed to be blocked. And considering the smammers are using 12374614187641874@optinmail.com along with other numerous addresses, it's impossible to block the majority of them. Hell I would even be happy if they would start allowing people to block entire domains. That would be a good first step.
My sig of choice is Marlboro
I have SpamAssassin at my isp (Verio) and it kicks ass. Probably a false positive per week (and that's often a slashdot Daily Stories email), and a false negative every 3-4 days. Pretty damn good. Cut inbox crapola from 10-20 per day to, well, zero.
sulli
RTFJ.
When someone would send you mail, it would send back a link to a small image, in the image was a 'click here' dot, only a human (or some software that no spammer would take the time to write) can get their email into your mailbox.
.com "troubles".
Kind of offensive though, a lot of people took offence to clicking a link to send me email.
MsgTo.Com dissappeared some time ago during the
Hedley
"Completely automated public test to tell males and females apart".
.....
a/s/l?
"18f,Florida"
Do you mind if I ask you to take a quick Captmfa?
"Sure, go ahead"
Test completed. Result = 34m, Detroit.
Now if they could just come up with a turing test for slashdot
2 /1 2/30/1740211&mode=thread&tid=111
repeats!
http://developers.slashdot.org/article.pl?sid=0
Granted this is not a direct repeat but the articles are just different sources for the same story.
-- The morphemes of your disquisition are ascertainable, but they have eschewed an ambit of transpicuous exposition.
I recently had to create an e-mail address that I could use for posting to a mailing list where the addresses are all public. I tried Hotmail first, and although I passed part 1 of their Turing test, the captcha test, I think I failed part 2: once I was all done filling in my personal information (retired female homemaker in Antarctica, born in 1891), I got some kind of mystifying error message saying something about my .NET account (which I don't have). I guess if I was human, I'd have been able to figure out what they meant.
Oh well, I passed Yahoo's captcha test, and they didn't have a part 2...
As a recipient of spam, I also don't see this having any benificial effects. I gets lots and lots of spam from hotmail.com and yahoo.com addresses. They're all forged headers, so it doesn't matter that Yahoo and Hotmail have botproofing -- the accounts I'm getting spam from aren't even real Yahoo and Hotmail accounts. It's great that they're trying to make sure they aren't spam havens (and of course it costs them money if spammers use their services), but I really think the whole e-mail infrastructure needs reworking in order to get rid of spam. Sending e-mail should cost some token amount of money, and there should also be some way of tossing out mail with forged headers (e.g., my mail client should be able to tell whether the cryptographic signature on an e-mail indicates that it really came from hotmail.com or yahoo.com).
Find free books.
click mail options:
go to
"Enter email address (or domain) to block:"
enter domain in text baox, such as
whatever.com
click, add block
The Kruger Dunning explains most post on
Yes, it's possible, and has been done recently by some guys in CS at Berkeley. Breaking captchas had always been posed as an open challenge to the AI/image processing community.
NY Times article
Berkeley press release
Computer vision pages (w/papers)
Greg's page on breaking Gimpy
These Turing tests do not stop spam. They discourage spammers from using bogus Hotmail etc accounts to originate spam from. They do this by making it incrementally more expensive to create the accounts; rather than using a bot to create an account a second you have to use a human to create accounts by the minute. So 60 times the effort.
But I don't think that translates into 60 times the cost. The Turing tests are interesting but I don't think that the creation of the accounts ever was a bottleneck in the process in sending spam. You could get a high school kid to create all the accounts you would need for a month in about an hour, and pay him in pr0n.
If the truth were known, Hotmail and Yahoo are just trying to decrease server loads. I bet that when bots create accounts they create hundreds or thousands more than are used, which take up server resources during creation and later as the accounts eat up storage. With Turing tests it is more likely that not too many will be laying around waiting to be used.
=^..^= all your rodent are belong to us
It works with Outlook (not Outlook Express).
The coolest part is when you find an email that is spam, which it didn't catch (perhaps about 5% of the time), just click "Block" and it'll record that you blocked it on their servers, so anyone else receiving the same (or nearly similar, I think) email will have it blocked as well.
In other words, it's a community-driven spam blocker which works better the more people use it. And it already works very well.
I feel fantastic, and I'm still alive.
I see a lot of posts here comparing the relative merits of different spam filters, based on how little spam gets through. The thing I worry about a lot more with spam filters is how much of my non-spam mail gets blocked. And yes, I've had this happen with every spam filtering mechanism some sysadmin has inflicted on me. This is the main reason I like spam filtering at the user level, not the ISP or system level -- at least you have some control over the imperfections.
This idea means licensing them so that they are properly registered, Meaning we know who they are and where they live.
Meaning that they can be billed for use of service, etc. and jail those not properly licensed.
Meaning that we can send bill collectors and tax collectors hunting after them.
The bottom line is that IF we can make it profitable to go after these guys, someone will make a business of it. We just go to figure a way how.
Then we get to use the scum of society, such as bill collectors and tax collectors, and turn them to some good, going after spammers.
And we can use the money collected to subsidise the cost of something useful.
Now Lessig has also proposed something similar to this:
http://www.cioinsight.com/article2/0,3959,533225,0 0.asp
Which essentially means that there are more eyeballs to track the scum down. And a financial reward to do so.
The twist in my proposal is to mach spam have a cost even if sent "legally" - [lots of states have finance problems], and make the penalties truly painful if done illegally. I want to set my own fees for receiving spam
"It is a greater offense to steal men's labor, than their clothes"
I've watched Spamarrest movie. The exactly same system (you have to read a word, obscured to defeat OCR programs) is beeing used by one of Polish mobile phone operators. If you want to send SMS from www->sms gate you also have to read a word. You can see it here.
:wq
The graphics basically don't work with OCR.
I wrote Yahoo about this problem just about a year ago, after
finding no explanation in their online help on about how
visually impaired users were supposed to use their service,
and this is what they had to say.
I kind of thought this sucked, that apparently the solution
is to wait for a human operator to read the feedback
form and phone you back. Surely someone can come up with
a better system.
=-=-=-=
Hello,
Thank you for writing to Yahoo! Account Services.
If you are a visually impaired or blind user, please fill out the
feedback form at:
http://add.yahoo.com/fast/help/us/edit/cgi_access
A customer care representative will call you back, to assist you with
registering for a Yahoo! account.
If we can be of further assistance, please let us know.
Thank you again for contacting Yahoo! Customer Care.
Regards,
Yahoo! Customer Care
For assistance with all Yahoo! services, please visit:
http://help.yahoo.com/
What do you get if you eliminate the human from the above? Why, a protocol link. Might as well require me to type in TCP/IP packets and consider me human if I make too many erorrs :-)
Welcome to the net of 1000 lies. Upgrades are scheduled soon that should bring us to the 10,000 lies mark.
Bayesian techniques depend on predicting which elements (usually, which words) are likely to indicate spam, and which are likely to indicate non-spam messages. This can vary highly from user to user, and so it should be done on a per-user basis.
For instance, I am a security administrator and receive a lot of legitimate mail about "antivirus software", and very little legitimate mail about "teenage lesbians." However, my girlfriend's crush, who is an activist lesbian, may well receive a lot of legitimate mail about "teenage lesbians" and only spam about "antivirus software." If we are on the same ISP, then it would be erroneous behavior for my reporting "teenage lesbians" as spam and "antivirus software" as nonspam to throw her spam-filtering out of whack, or vice versa. And yet it is a potential privacy violation for the ISP to be gathering statistics on which one of us gets virus bulletins, and which one is the lesbian.
(Moreover, there also isn't yet any standard mechanism for users to report spamminess or nonspamminess back to normal IMAP or POP mail hosts -- and Bayesian algorithms require sampling both spam and non-spam mail, not just spam reported to an abuse address.)
The filtering mechanisms that should be implemented on the server are general ones -- ones that do not rely on deep inspection into the content of the message. I don't really want ISPs to gather stats on common keywords in users' incoming mail -- do you? It is one thing to examine structural elements of the message, such as the IP address which sent it, or the presence of normal headers; or to statelessly scan the message for static patterns, such as virus signatures or "DISCOUNT HERBAL VIAGRA !!!" It would be quite another thing to gather the kind of data that Bayesian filters involve, for every user on a large end-user system.
An "autonated Turing test" is an oxymoron.
The Turing test is where a human talks to a computer and tries to decide if the backend that's answering him is a human or a computer program.
This is more of a reverse turing test, where the computer asks questions to try and find out if it's interacting with a person or a program.
It would be possible to write a program to beat this system, but it would not qualify as having passed the Turing test, because it would have only fooled another computer program, not a real person. Of course maybe said program could go on to pass the Turing test.
Wouldn't it be weird if spam was the driving force behind the creation of the first real AI?
Skynet began learning at a geometric rate.......by 1800 hours every mailbox in the world was jammed with unfilterable spam.
Life is too short to proofread.
I have this to say about it
GET IT.
I trained it on a corpus of spam I've been keeping around for just such a purpose (about 300 messages, not a lot really). Since then I have been giving it minor corrections to tag new spam and it is nearly perfect. No false positives. The interface is easy to use.
If you use Mozilla now for Mail, you owe it to yourself to start using the 1.3a. If you're using something else, it's worth looking at Mozilla.
From my understanding, the use of image recognition in the captcha test would make it nearly impossible for blind people to pass the test.
6) Profit!
Pain lasts, kid. Its how you know you're alive. Sometimes I think this growing up thing is just pain management-TheMaxx
Turing test is a bit of an exaggeration. They have you look at some garbled text and type what you see. And it's been going on for a very long time.
The Register article had absolutely nothing of value to add. As you were.
Donate background CPU time to fight cancer.