'Virtual Lolita' aims to trap chatroom paedophiles
The Negobot strikes up conversations to catch paedophiles in online chatrooms Continue reading the main story
Spanish researchers have created a robot posing as a 14-year-old girl to spot paedophiles in online chatrooms. tao mau nhanh , dich vu tao mau nhanh , tao mau nhanh gia re , dich vu tao mau nhanh gia re Negobot uses artificial intelligence (AI) software to chat realistically and mimic the language used by teenagers.
The "virtual Lolita" starts off neutral but will adopt any of seven personalities according to the intensity of interactions.
Experts say it can help overburdened police but may risk trapping people unfairly.
The team behind the project at the University of Deusto near Bilbao say the software represents a real advance. One of its creators, Dr Carlos Laorden, said that in the past "chatbots" have tended to be very predictable. "Their behaviour and interest in a conversation are flat, which is a problem when attempting to detect untrustworthy targets like paedophiles," he noted.
By contrast, the Negobot uses advanced decision-making strategies known as "game theory" to simulate convincing chats as they develop.
It can take the lead in conversations, and remember specific facts about what had been talked about earlier, and with whom.
Youngster-like behaviour The so-referred to as conversational agent also uses youngster-like language and slang, introducing spelling blunders and contractions to more spoof the predator.
Negobot would be used in a chatroom in which suspected paedophiles are imagined to be lurking. It initiates a chat as a relatively passive participant. It then adapts its behaviour according to the grooming strategies used by the suspect to try out to acquire above its have confidence in and friendship.
For illustration, if the suspect does not look to be enticed into possessing a conversation, the software can look offended or get a lot more insistent.
And it will reply to a lot more intense improvements - like requests for private details - by making an attempt to locate out a lot more about the suspect. This can contain specifics this sort of as their social community profile and cellular amount, details which can then be used by police to commence an investigation.
John Carr, a United kingdom federal government adviser on youngster defense, welcomed any go to reduce the load on real-planet policing. But he warned the software risked engaging people to do items they in any other case would not.
"Undercover functions are incredibly source-intense and sensitive items to do. It is totally essential that you do not cross a line into entrapment which will foil any prospective prosecution", he said.
To day, the software has been discipline examined on Google's chat support and could be translated into other languages. It has presently captivated the focus of the Basque police pressure.
But researchers confess that it does have constraints and will want to be monitored. Though it is has wide conversational capabilities, it is not but refined adequate to detect specific human characteristics like irony.