Sockpuppet-Detection Algorithms | Bitcointalksearch.org

helloworld

sr. member

Activity: 266

Merit: 250

Quote from: niko on October 30, 2012, 12:48:53 AM

Quote from: caffeinewriter on October 30, 2012, 12:27:57 AM

I think this is similar to the security concerns that surround Open Source software. Sure, proprietary companies keep their source a secret, but when it's open source, the community can push out a fix instead of waiting for the company to do it. Not to mention everyone can improve upon it.

Yep, everyone can improve upon it Cheesy

including the perpetrator!

But that's the same for forensic science. A perpetrator could spend years studying police investigation methods in order to fool them or evade detection and they may well be successful, but the other 99.99% of perpetrators won't spend years studying this, and will get caught out.

Likewise, the publishing of every known sockpuppetry detection method would only affect the minority of puppet masters that choose to study first and become experts at fooling the algorithms. I'm guessing that would be a very small minority as most wouldn't take the time to do this.

helloworld

sr. member

Activity: 266

Merit: 250

Quote from: MysteryMiner on October 30, 2012, 12:50:24 AM

Can someone find my alternate profiles?

Keep in mind most of us only have access to half the data (what's public).

The other data set would be stuff like IP addresses, access logs (which pages were viewed, which links were clicked, and at what time, etc).

MysteryMiner

legendary

Activity: 1512

Merit: 1049

Death to enemies!

Can someone find my alternate profiles?

And no, Atlas is not my alter-ego!

niko

hero member

Activity: 756

Merit: 501

There is more to Bitcoin than bitcoins.

Quote from: caffeinewriter on October 30, 2012, 12:27:57 AM

I think this is similar to the security concerns that surround Open Source software. Sure, proprietary companies keep their source a secret, but when it's open source, the community can push out a fix instead of waiting for the company to do it. Not to mention everyone can improve upon it.

Yep, everyone can improve upon it Cheesy

including the perpetrator!

caffeinewriter

hero member

Activity: 532

Merit: 500

Quote from: helloworld on October 30, 2012, 12:12:16 AM

Quote from: niko on October 30, 2012, 12:01:28 AM

Whatever algorithm you come up with, if you describe it in public it will quit working from that point on.

I very much doubt that, although it's effectiveness might reduce slightly.

The public description of ponzi schemes does not stop people falling for them.

And police catch criminals using fingerprint matching. This is well-known, and still works despite everyone knowing that they do this.

Still though, you bring up another dimension to the issue: Would researching and designing a system be made more difficult by those who would rather such detection methods remain secret?

I think this is similar to the security concerns that surround Open Source software. Sure, proprietary companies keep their source a secret, but when it's open source, the community can push out a fix instead of waiting for the company to do it. Not to mention everyone can improve upon it.

helloworld

sr. member

Activity: 266

Merit: 250

Quote from: niko on October 30, 2012, 12:01:28 AM

Whatever algorithm you come up with, if you describe it in public it will quit working from that point on.

I very much doubt that, although it's effectiveness might reduce slightly.

The public description of ponzi schemes does not stop people falling for them.

And police catch criminals using fingerprint matching. This is well-known, and still works despite everyone knowing that they do this.

Still though, you bring up another dimension to the issue: Would researching and designing a system be made more difficult by those who would rather such detection methods remain secret?

niko

hero member

Activity: 756

Merit: 501

There is more to Bitcoin than bitcoins.

Whatever algorithm you come up with, if you describe it in public it will quit working from that point on.

myrkul

hero member

Activity: 532

Merit: 500

FIAT LIBERTAS RVAT CAELVM

I'm sure this thread will help you test your algorithms. The inevitable pony-themed companion thread will help, too.

helloworld

sr. member

Activity: 266

Merit: 250

Quote from: caffeinewriter on October 29, 2012, 10:41:39 PM

Quote from: helloworld on October 29, 2012, 10:34:20 PM

Here's a conundrum:

I'd assume that alt accounts are more likely to agree with points raised by their primary account (although some would also be set up to argue), but what would the percentages be? e.g. 99% of alts align their views with their primary account, and 1% argue opposing points, or would it be closer to say, 60/40?

You could probably write an entire thesis (and more) on the topic, and if I were still in college, perhaps that's what I'd do.

Hmm, I can see the title now.

"Detecting Recurring Patterns Between Accounts To Find Individual Users with Multiple Accounts"

Maybe compare the users' introduction posts in the "Introduce Yourself" thread.

Except accounts on internet forums would be just a small subset of the research.

Detectives already do similar stuff IRL when someone forges a signature, or steals an identity. The signature may look okay to the naked eye, but up close it has very specific traits that can identify the real writer.

Although I am interested in the programming aspect, it's not really an I.T. topic at heart. It's probably more psychological / social.

caffeinewriter

hero member

Activity: 532

Merit: 500

Quote from: helloworld on October 29, 2012, 10:34:20 PM

Here's a conundrum:

I'd assume that alt accounts are more likely to agree with points raised by their primary account (although some would also be set up to argue), but what would the percentages be? e.g. 99% of alts align their views with their primary account, and 1% argue opposing points, or would it be closer to say, 60/40?

You could probably write an entire thesis (and more) on the topic, and if I were still in college, perhaps that's what I'd do.

Hmm, I can see the title now.

"Detecting Recurring Patterns Between Accounts To Find Individual Users with Multiple Accounts"

Maybe compare the users' introduction posts in the "Introduce Yourself" thread.

helloworld

sr. member

Activity: 266

Merit: 250

Here's a conundrum:

I'd assume that alt accounts are more likely to agree with points raised by their primary account (although some would also be set up to argue), but what would the percentages be? e.g. 99% of alts align their views with their primary account, and 1% argue opposing points, or would it be closer to say, 60/40?

You could probably write an entire thesis (and more) on the topic, and if I were still in college, perhaps that's what I'd do.

caffeinewriter

hero member

Activity: 532

Merit: 500

Quote from: MysteryMiner on October 29, 2012, 09:51:58 PM

Quote from: caffeinewriter on October 29, 2012, 09:21:35 PM

Similar signatures/same website on profile might also help.

Quote

most suckpuppet masters might fall on lower 20% on IQ scale.

Is this this case?

If this, then that.

MysteryMiner

legendary

Activity: 1512

Merit: 1049

Death to enemies!

Quote from: caffeinewriter on October 29, 2012, 09:21:35 PM

Similar signatures/same website on profile might also help.

Quote

most suckpuppet masters might fall on lower 20% on IQ scale.

Is this this case?

caffeinewriter

hero member

Activity: 532

Merit: 500

Similar signatures/same website on profile might also help.

MysteryMiner

legendary

Activity: 1512

Merit: 1049

Death to enemies!

If the algorithm detects that masters have low IQ but the stuckpuppets have high IQ then we have a problem LOL

Quote from: paraipan on October 29, 2012, 09:06:34 PM

Quote from: MysteryMiner on October 29, 2012, 08:57:10 PM

The average IQ level for all posts will also help at suckpuppet detection. The problem might be that most suckpuppet masters might fall on lower 20% on IQ scale.

Proof or STFU

Are You a stuckpuppet master?

paraipan

legendary

Activity: 924

Merit: 1004

Firstbits: 1pirata

Quote from: MysteryMiner on October 29, 2012, 08:57:10 PM

The average IQ level for all posts will also help at suckpuppet detection. The problem might be that most suckpuppet masters might fall on lower 20% on IQ scale.

Proof or STFU

They obviously have a higher than the average IQ and suffer some multiple personality disorder, so they can keep a good level of post quality if they wanted to, or the agenda requires it.

helloworld

sr. member

Activity: 266

Merit: 250

Quote from: MysteryMiner on October 29, 2012, 08:57:10 PM

The average IQ level for all posts will also help at suckpuppet detection. The problem might be that most suckpuppet masters might fall on lower 20% on IQ scale.

That would probably depend on how easily they were detected!

The dumb or careless puppet masters would be more obvious while the high-IQ alts would probably be more conscious of their traits and hence be better at flying under the radar.

MysteryMiner

legendary

Activity: 1512

Merit: 1049

Death to enemies!

The average IQ level for all posts will also help at suckpuppet detection. The problem might be that most suckpuppet masters might fall on lower 20% on IQ scale.

helloworld

sr. member

Activity: 266

Merit: 250

Quote from: P_Shep on October 29, 2012, 07:53:55 PM

Language is pretty easy.

Form a histograms of:
Syllables per word
Words per sentence
Sentences per paragraph.
Vocabulary.

And ratio of exclamation marks to word count!!!

Thanks, keep 'em coming

paraipan

legendary

Activity: 924

Merit: 1004

Firstbits: 1pirata

Quote from: P_Shep on October 29, 2012, 07:53:55 PM

Language is pretty easy.

Form a histograms of:
Syllables per word
Words per sentence
Sentences per paragraph.
Vocabulary.

And use of CR's in every post too

Topic: Sockpuppet-Detection Algorithms (Read 2029 times)