Paul Graham on Fighting Spam

Ramakrishnan M writes "Paul Graham, the Lisp Guru is back with a great technique to fight spam. It is based on trust matric, and he claims, only 5 out of 1000 spams got leaked out of this system with 0 false positives. Worth looking at."

I heard about this!

[WilliamsDA]

I got an email last night about this! Also, it asked me to help out his Nigerian cousin...

only 5 per 1000?

[jeffy124]

that means CmdrTaco reduces his spam intake to around 500/day.

Major geek bias there...

[Kaa]

From the article:

Based on my corpus, "sex" indicates a .97 probability of the containing email being a spam, whereas "sexy" indicates .99 probability. And Bayes' Rule, equally unambiguous, says that an email containing both words would, in the (unlikely) absence of any other evidence, have a 99.97% chance of being a spam.

Hmm.... take an average adult geek and yes, an email mentioning sex or sexy can go to /dev/null immediately without as much as a second glance... :-)

On the other hand if you run the statistics on email of an average horny teenager, the probabilities might get a bit different.

(spam)

[Anonymous Coward]

(insert (lisp joke (here)))

Re:Best anti-Spam method is TMDA

[Anonymous Coward]

"verified that they are a real person and not a spammer."

Heh, spammers are people too, you know :-)

False positives...

[dillon_rinker]

From the article:

In the spam filtering business, false positives are your biggest worry...Based on my corpus, "sex" indicates a .97 probability of the containing email being a spam, whereas "sexy" indicates .99 probability...an email containing both words would have a 99.97% chance of being a spam.

False positives could be a HUGE problem in this case...imagine the agony if you missed this email from your wife: "I'm feeling REALLY sexy today - meet me at the motel off 12th street at noon for some lunch-hour sex!"

Shifman

[T-Kir]

I wonder what Bernard Shifman would make of this article?

What is our 'CS Consultant' up to these days?

You're being shortsighted

[David Wong]

It was with the help of spam that with just a simple herbal supplement I was able to add three inches to my penis (an increase of over 20%). I had assumed it was just a scam, and nobody was more suprised than me that it worked.

Well, except my wife.

Re:spamassasin

[Unknown Bovine Group]

Based on my corpus, "sex" indicates a .97 probability of the containing email being a spam, whereas "sexy" indicates .99 probability. And Bayes' Rule, equally unambiguous, says that an email containing both words would, in the (unlikely) absence of any other evidence, have a 99.97% chance of being a spam.


Obviously, the author just isn't sexy.

Re:Major geek bias there...

[LordNimon]

But what about the (unlikely) situation of a geek getting a girlfriend? All of her steamy email will be flagged as spam, and then she'll get upset and dump him. Oh, the irony!

Great quote

[fizban]

This is the best paragraph of the whole article:

So as spammers start using "c0ck" instead of "cock" to evade simple-minded spam filters based on individual words, Bayesian filters automatically notice. Indeed, "c0ck" is far more damning evidence than "cock", and Bayesian filters know precisely how much more.

The Bayesian filter. You can run, but you can't hide!

Re:Easy way to beat spam 100%

[alcmena]

if you like, can put things like "don't use me" in the ALT attribute of the image to avoid curious people that browse in text/disable graphics mode.

Better yet, use the alt text "CLICK HERE!" and everyone will assume it's some sort of ad and they will refuse to touch it with a ten foot pole. "CLICK HERE!" is like the web version of the radioactive symbol.

Re:Nicely done

[certsoft]

Enlarge <!-- elephant --> penis [etc..]

I think most elephants have a large enough penis already.

Re:spamassasin

[Anonymous Coward]

Actually, I'd recommend a combination between a nasty spam filter that kills off close to anything that might conceivably be spam and white-lists of senders who are automatically cleared.

Great idea! Where'd you get it? The article?