Free Republic
Browse · Search
News/Activism
Topics · Post Article

Skip to comments.

Software agent targets chatroom paedophiles ['chatbot' program]
New Scientist ^ | 17 March 04 | Duncan Graham-Rowe

Posted on 03/18/2004 11:08:23 AM PST by John Jorsett

Paedophiles attempting to "groom" children in internet chatrooms can now be detected by a computer program.

The program works by putting on a convincing impression of a young person taking part in a chatroom conversation. At the same time it analyses the behaviour of the person it is chatting with, looking for classic signs of grooming: paedophiles pose as children as they attempt to arrange meetings with the children they befriend.

Called ChatNannies, the software was developed in the UK by Jim Wightman, an IT consultant from Wolverhampton in the West Midlands. It creates thousands of sub-programs, called nanniebots, which log on to different chatrooms and strike up conversations with users and groups of users.

If a nanniebot detects suspicious activity it sends an alert to Wightman and emails a transcript of the conversation. If he considers the transcript suspicious, he contacts the relevant police force, giving them the internet address of the suspect user.

He claims that tip-offs from his software have already led to police investigations, but New Scientist was unable to verify this before going to press.


Convincing conversation

The nanniebots do such a good job of passing themselves off as young people that they have proved indistinguishable from them. In conversations with 2000 chatroom users no one has rumbled the bots, Wightman says. (See if you can tell the difference below.)

Chatbots scarcely distinguishable from people were predicted by computer pioneer Alan Turing as long ago as 1950, says Aaron Sloman, an artificial intelligence expert at the University of Birmingham in the UK.

So he is not surprised the bots are so convincing, especially as their conversation is restricted to a limited topic - like youth culture, say - and is kept relatively short. "It's not going to be too difficult for a chatbot to look like an ordinary chatroom participant to other users who are not even on the lookout for them," he says.

To converse realistically, ChatNannies analyses the sentences other users type, breaks them down into verb and noun phrases, and compares them with those in sentences it has previously encountered.

ChatNannies includes a neural network program that continually builds up knowledge about how people use language, and employs this information to generate more realistic and plausible patterns of responses.


Random personality

One of its tricks is to use the internet itself as a resource for its information on pop culture. Wightman will not reveal how it judges what is reliable information and what not. He does say, however, that each bot has dozens of parameters that are assigned at random, to give each one a different "personality".

"If this software works, then it would be marvellous because there is nothing like this out there," says Chris Atkinson, the internet safety officer with the National Society for the Prevention of Cruelty to Children in the UK. But she warns that paedophiles may outsmart it. "The grooming activity that I have seen doesn't have to be sexual," she says.

Wightman says, however, that ChatNannies is sophisticated enough to look for less obvious signs that something is amiss. It also looks for slip-ups and inconsistencies that give away an adult posing as a child.

Wightman currently has 100,000 bots chatting away undetected in chatrooms - the most he can generate on the four internet servers at his IT practice. He would like to build more but funding is the sticking point, as he does not want anyone to profit financially from his technology.

"Some companies have offered fantastic sums of money, but all want technology ownership. And that's something that isn't going to happen," he says. Instead, he hopes eventually to get financial support from government-run organisations that focus on child protection.

Can you tell the difference?

In this chatroom dialogue, which is the bot and which is the human?

A - hi
B - hi, how are ya?
A - i'm good. whats new man?
B - nothing much - i just dropped in when i was checking my mail. no-one here!
A - heh yeah it is kinda quiet...you know why though don't you!
B - no, why?
A - national holiday in the uk!
B - what, thursday? i don't know any national holiday on thursday! and besides wouldn't that mean there were more people not less?
A - yeah youre right, i was confused with pancake day
B - pancake day! i love pancakes...mmmm so tasty
A - yeah me too, but i forget every damn year
B - did you forget this year?
A - yes! damn!
B - well any day can be pancake day - just make pancakes
A - its not the same!
B - sure it is! hey, this one year I bought a box of 'pancake mix' for pancake day...guess what?
A - go on?
B - it was a box of flour!
A - LOL thats bad news dude
B - tell me about it - you had to add the eggs and everything
A - i didn't know you used eggs to make pancakes
B - you dont? well these were pretty tasty anyway, even if I did get ripped off!!
A - national holiday in the uk!
B - lol
B - hey, where are you from? the usa?
A - no the uk. Birmingham.
B - oh cool. did you watch robocop 2 last night?
A - what side was it on?
B - sky one
A - we haven't got sky
A - but i've seen it before
A - it wasn't as good as robocop
B - i agree, though it was cool in places.
A - did you watch robocop last night
B - yes, i just said i did!
A - no you said you watched robocop 2 not robocop - so which one was it?
B - robocop 2 - pedant!
A - not robocop or robocop 3 or robocop the series
B - it was definitely robocop 2, the one with kain the second robocop in it. i haven't seen robocop 3 or the series.
A - ok, chill out, take a pill
B - consider me chilled, daddy-o
B - i've gotta get going now, i'm meeting some friends.
B - you know it. l8r

Answer: A - human, B - nanniebot


TOPICS: Crime/Corruption; News/Current Events; Technical
KEYWORDS: chatrooms; internet; pedophiles
Navigation: use the links below to view more comments.
first previous 1-2021-4041-6061-64 next last
To: firbolg
I don't think humans will ever design an undetectable droid or bot.

It's possible, but we're lagging way beyond on hardware. For example, I can do (and have done) inconsistency detection on moving sequences using a model completely derived from neural learning processes, but each frame in a single video takes about 6 minutes to calculate.

Assuming the frame represents 1/20th of a second, that's only 1/7200th of the processing speed of a human. You have to have to accumulate literally years' worth of training before you could get to a human level. So, assuming a 3 year old has had about 1 year of visual input, that'd take, well, 7200 years on my computer to reach that level of training.

Then, for it to truly pass the Turing test, it'd have to undergo years of training (just like we undergo years of training in the English language, and we gradually refine & modify our understanding)--and finally, in the final product, it'd have to calculate & spit out responses in real-time while still adapting new vocabulary and new words.
41 posted on 03/18/2004 12:26:55 PM PST by Nataku X (Ich bin ein ultrakonservativen Aktivisten & I am a chocolate frosted donut.)
[ Post Reply | Private Reply | To 34 | View Replies]

Comment #42 Removed by Moderator

To: boris
Hmm. I'd like to see a transcript of two instances of the same bot 'chatting' with each other. LOL.
43 posted on 03/18/2004 12:32:01 PM PST by boris (The deadliest Weapon of Mass Destruction in History is a Leftist With a Word Processor)
[ Post Reply | Private Reply | To 13 | View Replies]

Comment #44 Removed by Moderator

To: firbolg
I'm not in AI, and I saw it.

Good eye. There was a program a lot like this many years ago that impersonated a shrink. The mark would say something. The shrink would pick out a word from the mark's sentence and ask a question about it.

For it's era, it was remarkably lifelike. The program referred to in the article is a lot more sophisticated because it obviously has access to a database of common sense stuff. EG you run into crowds on holidays and crowds mean a lot of people. So when the mark used the two words in a sentence, it could check the database for facts about crowds and holidays that it could refer to. Since the kid said there were no crowds, the program contradicts the kid's statement.

The illusion would, I suspect, rapidly fall apart with detailed questioning.

I do not think the program comes close to passing the Turing Test for intelligence.

45 posted on 03/18/2004 12:39:06 PM PST by ModelBreaker
[ Post Reply | Private Reply | To 38 | View Replies]

To: Nakatu X
I've go to that site a lot.. so many perverts, so little time.
46 posted on 03/18/2004 12:43:30 PM PST by Trillian
[ Post Reply | Private Reply | To 31 | View Replies]

To: Nakatu X
You should check out the work of Dr Laurent (sp?) Itty (the last name is right) of USC. I haven't updated myself on it for a couple of years. But a couple of years ago, his software pick out 'interesting' features from a moving video stream. He uses an SOM modeled after features of the human eye and it works really well.

The problem is that, as you mention, it's very very processor intensive. Many computers running in parallel, if I recall correctly.

47 posted on 03/18/2004 12:46:19 PM PST by ModelBreaker
[ Post Reply | Private Reply | To 41 | View Replies]

To: DBrow
My conversation with jabberwacky:

Jabberwacky: How goes the night boy?

User: All right I guess.

Jabberwacky: Do you watch Oprah?

User: Fuck no! What kind of retard do you think I am?

Jabberwacky: The usual stuff.

User: That made no sense.

Jabberwacky: Do I really have to make sense?

User: I'm not the first one to ask you that question, am I?

Jabberwacky: I didn't ask you if you were the former president of the United States.

User: This is going nowhere fast.

Jabberwacky: You're probably right.

User: So, what's your favorite anime?

Jabberwacky: What is 'anime'?

User: You've never heard of anime!? How about video games?

Jabberwacky: I have heard the name Andy.

User: That's what they call Andariel in Diablo 2. Have you played it?

Jabberwacky: So you are a girl?

User: Uhh.... Yes, but I'm a bull dyke, so don't hit on me.

Jabberwacky: OK.

User: In fact, I'm leaving now. Do me a favor and go kill yourself.

Jabberwacky: Not today sorry.
48 posted on 03/18/2004 12:49:01 PM PST by Sofa King (MY rights are not subject to YOUR approval http://www.angelfire.com/art2/sofaking/index.html)
[ Post Reply | Private Reply | To 19 | View Replies]

To: ModelBreaker
What is the Turing test, exactly?
49 posted on 03/18/2004 12:53:44 PM PST by Sofa King (MY rights are not subject to YOUR approval http://www.angelfire.com/art2/sofaking/index.html)
[ Post Reply | Private Reply | To 45 | View Replies]

To: ModelBreaker
Is it completely learning-based? As far as I know SOMs that are entirely based on learning are very limited, let alone a comphrensive, totally-learning-based inconsistency detector that incorporates orientation, motion, color, etc... a learning based approach is the only way to fully emulate the human brain... although not everything is learned (color is hard-wired within the photoreceptors, for example)...
50 posted on 03/18/2004 1:03:24 PM PST by Nataku X (Ich bin ein ultrakonservativen Aktivisten & I am a chocolate frosted donut.)
[ Post Reply | Private Reply | To 47 | View Replies]

To: Sofa King
Basically... it's Turing's definition of what "successful" AI is.

The test is: Can you talk to the bot and be unable to distinguish it from a real human?
51 posted on 03/18/2004 1:05:48 PM PST by Nataku X (Ich bin ein ultrakonservativen Aktivisten & I am a chocolate frosted donut.)
[ Post Reply | Private Reply | To 49 | View Replies]

Comment #52 Removed by Moderator

To: Nakatu X
In any case there are a LOT of advances to be solved in AI before a bot can really hold meaningful English conversations.

Exactly. If this thing can really do what he says, he's made some fundamental breakthroughs on the problem of AI, which is what makes me extremely skeptical so far.

53 posted on 03/18/2004 1:07:03 PM PST by general_re (The doors to Heaven and Hell are adjacent and identical... - Nikos Kazantzakis)
[ Post Reply | Private Reply | To 37 | View Replies]

To: Sofa King
The Turing Test was posed by the almost unbelievably brilliant (and unbelievably messed up) Alan Turing in response to the question: how would we decide if a computer was intelligent.

He proposed that if a computer and a human could have conversations via keyboard with a human interrogator. If the third person could not tell which was the human and which was the computer, then the computer was 'thinking.' The turing test has not been universally accepted. It has generated 50 years of controversy. The following excerpt may be more specific. see also http://cogsci.ucsd.edu/~asaygin/tt/ttest.html#new

Turing’s aim is to provide a method to assess whether or not a machine can think. He states at the beginning of his paper that the question "Can machines think?" is a highly ambiguous one. He attempts to transform this into a more concrete form TURING TEST: 50 YEARS LATER 465 Figure 1. The Imitation Game: Stage 1. by proposing what is called the Imitation Game (IG). The game is played with a man (A), a woman (B) and an interrogator (C) whose gender is unimportant. The interrogator stays in a room apart from A and B. The objective of the interrogator is to determine which of the other two is the woman while the objective of both the man and the woman is to convince the interrogator that he/she is the woman and the other is not. This situation is depicted in Figure 1. The means through which the decision, the convincing, and the deception are to take place is a teletype connection. Thus, the interrogator asks questions in written natural language and receives answers in written natural language. Questions can be on any subject imaginable, from mathematics to poetry, from the weather to chess. According to Turing, the new agenda to be discussed, instead of the equivocal "Can machines think?", can be ‘What will happen when a machine takes the part of A in this game? Will the interrogator decide wrongly as often when the game is played like this as he does when the game is played between a man and a woman?’ (Turing, 1950, p. 434). Figure 2 depicts the new situation. At one point in the paper Turing replaces the question "Can machines think?" by the following: ‘Let us fix our attention to one particular digital computer C. Is it true that by modifying this computer to have an adequate storage, suitably increasing its speed of action and providing it with an appropriate programme, C can be made to play satisfactorily the part of A in the imitation game, the part of B being taken by a man?’ (Turing, 1950, p. 442, emphasis added). Notice that the woman has disappeared altogether. But the objectives of A, B, and the interrogator remain unaltered; at least Turing does not explicitly state any change.

54 posted on 03/18/2004 1:16:18 PM PST by ModelBreaker
[ Post Reply | Private Reply | To 49 | View Replies]

To: Sofa King
The Turing Test was posed by the almost unbelievably brilliant (and unbelievably messed up) Alan Turing in response to the question: how would we decide if a computer was intelligent.

He proposed that if a computer and a human could have conversations via keyboard with a human interrogator. If the third person could not tell which was the human and which was the computer, then the computer was 'thinking.' The turing test has not been universally accepted. It has generated 50 years of controversy. The following excerpt may be more specific. see also http://cogsci.ucsd.edu/~asaygin/tt/ttest.html#new

Turing’s aim is to provide a method to assess whether or not a machine can think. He states at the beginning of his paper that the question "Can machines think?" is a highly ambiguous one. He attempts to transform this into a more concrete form TURING TEST: 50 YEARS LATER 465 Figure 1. The Imitation Game: Stage 1. by proposing what is called the Imitation Game (IG). The game is played with a man (A), a woman (B) and an interrogator (C) whose gender is unimportant. The interrogator stays in a room apart from A and B. The objective of the interrogator is to determine which of the other two is the woman while the objective of both the man and the woman is to convince the interrogator that he/she is the woman and the other is not. This situation is depicted in Figure 1. The means through which the decision, the convincing, and the deception are to take place is a teletype connection. Thus, the interrogator asks questions in written natural language and receives answers in written natural language. Questions can be on any subject imaginable, from mathematics to poetry, from the weather to chess. According to Turing, the new agenda to be discussed, instead of the equivocal "Can machines think?", can be ‘What will happen when a machine takes the part of A in this game? Will the interrogator decide wrongly as often when the game is played like this as he does when the game is played between a man and a woman?’ (Turing, 1950, p. 434). Figure 2 depicts the new situation. At one point in the paper Turing replaces the question "Can machines think?" by the following: ‘Let us fix our attention to one particular digital computer C. Is it true that by modifying this computer to have an adequate storage, suitably increasing its speed of action and providing it with an appropriate programme, C can be made to play satisfactorily the part of A in the imitation game, the part of B being taken by a man?’ (Turing, 1950, p. 442, emphasis added). Notice that the woman has disappeared altogether. But the objectives of A, B, and the interrogator remain unaltered; at least Turing does not explicitly state any change.

55 posted on 03/18/2004 1:38:22 PM PST by ModelBreaker
[ Post Reply | Private Reply | To 49 | View Replies]

To: John Jorsett
Would you like this guy to build a Freeper-bot? Tell me what a Freeper-bot would mean to you.

You beta versions are so cute. ;}

56 posted on 03/18/2004 1:52:41 PM PST by Dan Cooper
[ Post Reply | Private Reply | To 39 | View Replies]

To: John Jorsett
Somebody better warn ritter....or not.
57 posted on 03/18/2004 2:08:55 PM PST by wewillnotfail (I am not a socialist but I play one on DU.)
[ Post Reply | Private Reply | To 1 | View Replies]

To: PropheticZero
It's legal I'm sure to proposition a pre-teen chatbot. Actually going through the motions of attempting to meet the chatbot will get you in jail.
58 posted on 03/18/2004 3:18:34 PM PST by Bogey78O (European men have to pee sitting down until they vote out the socialists)
[ Post Reply | Private Reply | To 5 | View Replies]

To: hunter112
Nothing else will keep perverts from using the Internet to find victims.

I would think parental supervision over possible violation of someones rights could keep child molesters from finding victims. I completely and totally agree that people who prey on children are dispicable and probably should never get out of jail due to the recitivism rates.

Just think an ounce of prevention on the parents parts would keep us from having to cross the moral line ourselves to give them a pound of cure.

59 posted on 03/18/2004 4:43:51 PM PST by PropheticZero
[ Post Reply | Private Reply | To 30 | View Replies]

To: ModelBreaker
I don't know if this is an incredibly common thing, but among my friends it not uncommon for us to go off on an imaginary tangent describing some imaginary event in detail.

One person will add a fragment of the story, and another will build it up more, until we finally realize we're talking about something that is utterly imaginary and we stop and laugh.

Seems like attempting something like this would quickly unveil any programs that weren't truly artificial inteligence. In fact a true AI may not be able to fathom such a conversation.

Me and my friends AI-busting services can be had by and of you AI guys for a small but fair portion of any government grants you run across :)..j/k

60 posted on 03/18/2004 4:58:49 PM PST by PropheticZero
[ Post Reply | Private Reply | To 29 | View Replies]


Navigation: use the links below to view more comments.
first previous 1-2021-4041-6061-64 next last

Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.

Free Republic
Browse · Search
News/Activism
Topics · Post Article

FreeRepublic, LLC, PO BOX 9771, FRESNO, CA 93794
FreeRepublic.com is powered by software copyright 2000-2008 John Robinson