Microsoft Researchers Slash Skype Fraud By 68%

mask.of.sanity writes "Life could become more difficult for fraudsters on Skype thanks to new research by Microsoft boffins that promises to cut down on fake accounts across the platform. The research (PDF) combined information from diverse sources including a user's profile, activities, and social connections into a supervised machine learning environment that could automate the presently manual tasks of fraud detection. The results show the framework boosted fraud detection rates for particular account types by 68 per cent with a 5 per cent false positive rate."

Comments

That's nice.

[pushing-robot]

So let me get this straight...

Your new filter works better than today's filter...against today's spam

But today's spam is designed to circumvent today's filter, and spammers will change their techniques as soon as you switch to the new filter.

This is the classic Antivirus problem, where new and unusual AV programs get great ratings until they become popular and virus developers start coding with them in mind.

And now you've also published how your new filter works, to make it even easier for spammers to circumvent your new filter. Great.

BAD MATH!

[CapOblivious2010]

Improving detection by 68% != Reducing fraud by 68%

Imagine that previous methods caught 10% of the fraudulent accounts. New tech improves that to 16.8%. It's a 68% improvement in the fraud detection rate, but only a 6.8% "slashing" of the fraudulent accounts.

(And 5% false positives is pretty horrific)

Re:BAD MATH!

[Baloroth]

TFS (and TFA, actually) are poorly phrased: the actual research article (the linked PDF) specifies (and I quote):

The aim of our work is to go beyond the present, sophis-ticated defenses, and to detect "stealthy" fraudulent users, namely, those that manage to fool those defenses for a relatively long period of time. Our concrete objective is to catch these stealthy fraudulent users within the first 4 months of activity. Our results indicate that, with our methods, we are able to detect 68% of these users with a 5% false positive rate; and we are able to reduce by 2:3 times the number of these users active for over 10 months.

So they didn't increase their detection rate by 68%, they increased it to 68%. And 5% false positive is pretty good: 95% confidence interval is standard in scientific research (outside things like physics which is able to achieve much much higher confidence by means of vastly larger data sets), which means a 5% false positive is exactly what you'd expect with proper scientific methodology ( based on a quick scan that seems to be exactly what they were aiming for). And of course higher false positive is actually better in the case of fraud detection than lower detection rate (since little is harmed by a false positive, while false negatives can directly result in people losing money).

Don't want a legitimate account

[Jack Griffin]

90% of my online accounts are fake, even this one. I create new accounts with new names to preserve my privacy, I have multiple hotmail, gmail and Facebook accounts specifically for this purpose. Sure the NSA types might see through this, but the average marketing agency won't. In real life, you can separate your worlds. My wife's circle of friends know me, but they don't know my friends, same goes for work 'mates', extended family etc. I have the power to keep things separate. It seems this choice is being slowly removed in online life as every web service demands you use your real name. Who wants to live in a world where everyone knows everything? We need a right to anonymity online.

Re:Lovely

[rmdingler]

Don't fall for it. Growing up is a Pyrrhic Victory.

You see...

[Chompjil]

Hangouts is doing wonders for me now so I dont mind if my skype account is shut down

What is skype fraud?

[mcmonkey]

I've only used skype a few times. What is skype fraud?

My understanding of skype is it's basically a video phone using your general purpose computer.

I read some of TFA looking for what types of fraud they are talking about, but didn't see any detail. They mention credit card fraud, but that's not a feature of skype. I mean, if some stranger knocks on your door, and when you answer, asks for your credit card number, and you give your credit card number, that's not a weakness in your door or lock, that's a weakness in you.

What I do with my landline is never answer if I don't recognize the number or name in the caller ID. Couldn't I do the same with skype, never answer if I don't know who is calling? There you go, 100% fraud prevention.