Slashdot Mirror
Twitter Eyes Signatures To Kill Fake Followers
mask.of.sanity writes "Researchers have developed a signature system being examined by Twitter that hold promise to cut down on the amount of fake accounts used to deliver spam and malware.
The signatures were developed during a study into the semi-underground market of fake accounts and was subsequently used by Twitter to eliminate an impressive 95 percent of several million accounts identified in the research. It applied elements like account names, the timing of the account creation, and browser identifiers to identify fake accounts. The 10-month study found that the creation of fake accounts at its peak represented 60 percent of all new accounts. (Paper here.)"
Considering an incredibly similar article is listed like 5 articles down.
http://blog.foreignpolicy.com/posts/2013/08/13/covert_twitter_ops_Israel_s_latest_misadventure_in_digital_diplomacy
There are ways of "inventing legitimate opinions" on the internet, living, breathing mechanical turks always pass the Turing test...
I think it's pretty important to recognize that people are scum often enough that you can predict when a popular service is out there, someone will attempt to game it in some way to defraud or otherwise deceive others for personal gain.
Sadly, some people call this "doing business." I simply can't agree with the morality, but I can't reject the reality of the situation.
It would be nice if online accounts like this had some sort of "longevity health" that was a function of how often they were updated (and when they were last updated). Every tweet, for example, would add some length of time onto the lifespan of an account, based on some kind of metric on how often people should be interacting with their stream (ie. 1/day or something like that).
When a user does not log into their account, a clock ticks down and when it hits zero, the account is archived and deactivated. The user can "reset" the countdown by logging into their account. And the more interacting they do while logged in the longer the countdown lasts while they are logged out.
May not be the best implementation, but it would just be nice to see some kind of auto-culling behavior on networks like these. Not just for spammers but for people who create an account, send three tweets about "what do I do on here?" and then never log in again. #namespacewaste
When the dust settles, the 50 people using twitter will be grateful that the bots have been kicked off their lawn.
FTFA:signatures built on elements like account names, the timing of the account creation and browser identifiers to identify fake accounts.
It would be wise for them to beta this tech first before actually implementing it full scale. For a $360M a year practice, there will be people who will find a way around it. Everyone thought Captcha was hackproof when it first came out and that has basically mutated into a system which can be used by neither human or machine.
Join the Slashcott! Feb 10 thru Feb 17!
I wonder what the false positive rate is for the signature system? The false negative rate is 5%. I would need to know more information before I could figure out the false positive rate and how many legitimate accounts are flagged by this system,.
Anyone remember Yahoo messenger?
Back in the day I found that they had a pretty nice search system. You could search by name, area, username, a bunch of stuff. The results, if clicked on, would lead to their profiles. I remember one day I searched for someone just out of curiosity to see if they were there. They lived in a small town of maybe 100 people. There were something like 10,000 users from that small town, all of them with long numbers in front of their name. Like 0000000amandaxxxfree and shit like that. Around that time, the Yahoo messenger spambots started. Every city I looked at had the absolute maximum number of users, and the first 90% of them were these names.
Yahoo never fixed it. Spam bots took over. At the peak of Yahoo spambots, I'd get 50 or 60 messages a day from different bots. The messages would be the same or at least very similar. They just didn't have the people or software to deal with it. Maybe Twitter learned.
If it's as lucrative as it seems to be to astroturf with spambots it seems inevitable that someone will find a way to do that.
The summary is a little misleading, it quotes a "peak" of fake accounts being "60 percent of the total new Twitter accounts," but leaves out the part of the article saying that over the 10-month study, the average was fake accounts were only "about 20 percent of new Twitter account created."
TFA also stated:
So I see no reason to think that, once a new "signature system" is put in place to cut down scam accounts, the scammers won't understand that and develop work-arounds as well.
http://www.geoffreylandis.com
someone will attempt to game it in some way to defraud or otherwise deceive others for personal gain.
You understand libertarian capitalism perfectly.
There's nothing wrong with doing business. Scamming occurs when one party in the negotiation (could be solicitor in some cases, but more often is the customer) leaves the exchange feeling jilted, decieved so as to give one party unfair advantage, or outright robbed. Any business exchange where one party is not completely honest is suspect.
Exactly. Free markets work well under the right conditions, but one of the things needed for free markets to be effective is an absence of widespread deceit.
So as long as you aren't aware you're being swindled by externalized costs, it's just fine. Yes.
Externalized costs are another way in which free markets fail to work well. Basically, if somebody can offload their cost, so that they get the benefits and somebody else pays the cost, the market is no longer efficient.
http://www.geoffreylandis.com
The researchers obtained permission from Twitter to conduct the research but were denied by Google, Yahoo and Facebook to conduct an investigation into scam accounts over their respective networks.
So only Twitter cooperated with an independent researcher trying to identify fake accounts. There is conflict of interest here, big companies have no real incentive to crack down on fake accounts. We should really commend Twitter for being open.
sed -e 's/Chuck Norris/Rajnikant/g' joke > fact
If you can get 10000 followers for a few bucks, why doesn't twitter set up fake accounts, pay the people to follow that account, then assume all followers are fake and delete those accounts. They could also determine the IPs and other identifiers around those accounts and block them in the future. If they have sweat shop people doing this, then the cost of creating accounts would be higher and likely not profitable.
Ninjas don't carry tic tacs
Won't this just result in bots that make signatures as well as posting/following?