Aviões-robô da Força Aérea americana são infectados por vírus ...

Aviões-robô da Força Aérea americana são infectados por vírus

De acordo com reportagem da revista Wired, drones Predator e Reaper foram contaminados com um malware que registrou os comandos enviados pelos militares.

Um vírus de computador infectou o cockpits dos aviões não-tripulados (drones) Predator e Reaper, registrando todos os comandos enviados para essas naves, usadas em missões de combate no Afeganistão, Iraque e outros lugares.

Segundo reportagem da Wired, o vírus, detectado há quase duas semanas pelos militares, não impediu as operações no exterior. Também parece não ter havido vazamento de dados. No entanto, o malware tem resistido ao esforço para limpá-lo do computadores da base da Força Aérea Creech, em Nevada (EUA).


Predator

Avião-robô Predator, controlado remotamente

"A gente o remove, mas ele continua voltando", disse uma fonte familiarizada com a infecção à revista. "Achamos que é benigno, mas simplesmente não sabemos."

Especialistas em segurança de redes militares não têm certeza se o vírus foi introduzido intencionalmente ou por acidente – pode tratar-se de um malware comum que se infiltrou pela rede. Eles também não sabem o quão longe a praga se espalhou. Mas é certo que a infecção atingiu máquinas que guardam dados comuns e outras com informações secretas. Logo, em tese, pode ser que segredos militares tenham sido enviados para o exterior.

Os chamados drones são controlados à distância, e permitem atacar e espionar inimigos sem arriscar soldados. Desde que Obama assumiu a presidência dos EUA, uma frota com cerca de 30 aviões destes, dirigida pela CIA, atacou alvos no Paquistão mais de 230 vezes; ao todo, mataram mais de 2.000 supostos militantes e civis, de acordo com o jornal Washington Post.

Mais de 150 Predator e Reaper, sob controle da Força Aérea, voam no Afeganistão e no Iraque. Drones foram usados em 92 ataques na Líbia, entre meados de abril e final de agosto.

Mas, apesar dessa importância estratégica, os sistemas dos drones são conhecidos por falhas de segurança. Muitos não codificam o vídeo enviado para as tropas em terra. Em 2009, os EUA descobriram "dias e dias e horas e horas" de filmagens em laptops de insurgentes iraquianos. Um software de 26 dólares permitiu a eles gravar as transmissões.

Drives externos
A maioria das missões dos drones são comandadas na base de Creech, no deserto de Nevada, a partir de salas chamadas GCS - Estação de Controle em Terra.

Teoricamente, nenhuma das naves está conectada à Internet pública, portanto, imune às ameaças da rede.

No entanto, o uso de drives removíveis acabou resultando na infecção de redes militares por vírus. Em 2008, por exemplo, milhares de máquinas do Departamento de Defesa foram contaminadas com o worm agent.btz, introduzido por um pendrive contaminado. Três anos depois, o Pentágono ainda está limpando o malware.

As equipes dos drones usam HDs externos para fazer updates nas naves e transportar os vídeos. Ao que tudo indica, foi por aí que o vírus entrou. Agora, estão todos proibidos de usar esses drives removíveis.

Técnicos estão tentando se livrar do vírus, mas não tem sido fácil, diz a reportagem. No início, seguiram instruções de remoção publicadas no site da Kaspersky. "Mas sempre volta", disse uma fonte à revista. O jeito foi usar uma ferramenta para formatar os HDs dos controladores, e recomeçar tudo do zero.

A Força Aérea dos EUA não quis comentar o assunto. "Está dando muita atenção a ele", disse a fonte. "Mas ninguém está em pânico. Ainda. "


http://idgnow.uol.com.br/seguranca/2011/10/07/avioes-robo-da-forca-aerea-americana-sao-infectados-por-virus/

Vão esperar serem atacados pelos próprios armamentos pra entrar em pânico... Norte Americano é ...

Isso tá parecendo ficção científica!
imagine se eles começarem a nos atacar!

Boss2K escreveu:

Foi um desses que bombardeou a casa do NETOULTRA mes passado ???????????

Boss2K escreveu: "Achamos que é benigno..."

esta foi p/ acabar...

ELISEUMOHR escreveu:Isso tá parecendo ficção científica!
imagine se eles começarem a nos atacar!

É .... a vida imita a arte ...

Em O Exterminador do Futuro 3: A Rebelião das Máquinas:

"... quando a SKYNET torna-se auto-consciente.quando um vírus entra nos computadores e as maquinas assumem o controle e partem para a guerra, ..."

Se isso aí aparece imagina o que não acontece por baixo dos panos.

Se levarem a inteligência artificial adiante, o domínio das máquinas é inevitável.

O raciocínio é bem simples.

Eles - Idiotas, destroem o planeta, jogam bombas uns nos outros, tem prazo de validade de 65 anos.

Nós - Pensamos mais rápido, somos mais eficientes, manutenção mais barata, prazo de validade de 800 anos.

Quem fica?

Esses equipamentos são demais!
Já operei um Drone Predador desses.....
No call of duty é claro rsrs
Podia dar pal e soltar um RPG bem na casa do Sarney.

Renato Reis escreveu:Podia dar pal e soltar um RPG bem na casa do Sarney.

O que seria dar pal?

allexcosta escreveu:

Renato Reis escreveu:Podia dar pal e soltar um RPG bem na casa do Sarney.

O que seria dar pal?

Eis a resposta: http://www.dicionarioinformal.com.br/definicao.php?palavra=dar+pau

^ Dar pau eu sei o que é...

Anyway...

allexcosta escreveu:

Se levarem a inteligência artificial adiante, o domínio das máquinas é inevitável.

O raciocínio é bem simples.

Eles - Idiotas, destroem o planeta, jogam bombas uns nos outros, tem prazo de validade de 65 anos.

Nós - Pensamos mais rápido, somos mais eficientes, manutenção mais barata, prazo de validade de 800 anos.

Quem fica?

Olha o caminho que isso tá tomando, Alex...




Se os dois chatbots do vídeo participassem do fórum o resultado seria um monte de tópicos trancados... rsrs

seria muito melhor ter escrito "dar pênis"...

fheliojr escreveu:seria muito melhor ter escrito "dar pênis"...

mas antes que os amantes das "teorias da conspiração" alucinem, inteligencia artificial ainda é beeeeeeem distante do que entendemos por inteligência humana.

inteligência artificial tenta indentificar novos padrões de comportamento de uma determinada coisa e se programado para tal pode reagir.
é pouquíssimo provavel pensar em um sistema totalmente auto-consciente como o a série "Exterminador do Futuro" propõe. (que aliás sou fanzaço)

portanto, podem relaxar que não veremos nada muito próximo disso nos próximos anos... ou meses... ou dias...

Não tente me enganar Denis, eu conheço o seu segredo:

DenisLM escreveu:portanto, podem relaxar que não veremos nada muito próximo disso nos próximos anos... ou meses... ou dias...

Sei não viu... Troquei uma idéia com a cleverbot dia desses e tem hora que a conversa não fica muito amigável.

Huummmm .... ... sei não, acho que longe não tá não ...

(desculpem mas, os textos estão todos em inglês)

ALVINN - Autonomous Land Vehicle In a Neural Net - This page describes one of the more interesting, and challenging neural net projects being undertaken - learning to drive. ALVINN is a system being designed at Carnegie Mellon University to learn basic rules of driving, and like all nets, improve with experience. (Infelizmente esse acesso está protegido por usuário e senha).

Real-world applications - Various interesting examples where NeuroSolutions have used neural network technology.

The Utah-Brain Project - is building an artificial brain which will control the behaviour of a life-sized robotic cat.

Java and ActiveX Nets - This site features 6 nets, some with tutorials, which are available in Java or ActiveX form. Sites like this offer promise in that they demonstrate that the power of neural computing can be made available online quite easily. The nets themselves may not be of much interest (they are designed to predict certain stock prices, or to learn mathematical functions like the cosine curve) but the tutorials are valuable. NOTE: The tutorials, as well as all demos in this section, will make more sense if you have done the assigned readings first.

Franklin's Intelligent Distribution Agent

Stan Franklin (1995, 2003) defines an autonomous agent as possessing functional consciousness when it is capable of several of the functions of consciousness as identified by Bernard Baars' Global Workspace Theory (Baars 1988, 1997). His brain child IDA (Intelligent Distribution Agent) is a software implementation of GWT, which makes it functionally conscious by definition. IDA's task is to negotiate new assignments for sailors in the US Navy after they end a tour of duty, by matching each individual's skills and preferences with the Navy's needs. IDA interacts with Navy databases and communicates with the sailors via natural language e-mail dialog while obeying a large set of Navy policies. The IDA computational model was developed during 1996–2001 at Stan Franklin's "Conscious" Software Research Group at the University of Memphis. It "consists of approximately a quarter-million lines of Java code, and almost completely consumes the resources of a 2001 high-end workstation." It relies heavily on codelets, which are "special purpose, relatively independent, mini-agent[s] typically implemented as a small piece of code running as a separate thread." In IDA's top-down architecture, high-level cognitive functions are explicitly modeled (see Franklin 1995 and Franklin 2003 for details). While IDA is functionally conscious by definition, Franklin does "not attribute phenomenal consciousness to his own 'conscious' software agent, IDA, in spite of her many human-like behaviours. This in spite of watching several US Navy detailers repeatedly nodding their heads saying 'Yes, that's how I do it' while watching IDA's internal and external actions as she performs her task."

Ron Sun's cognitive architecture CLARION

CLARION posits a two-level representation that explains the distinction between conscious and unconscious mental processes.

http://www.cogsci.rpi.edu/~rsun/clarion.html

CLARION has been successful in accounting for a variety of psychological data. A number of well-known skill learning tasks have been simulated using CLARION that span the spectrum ranging from simple reactive skills to complex cognitive skills. The tasks include serial reaction time (SRT) tasks, artificial grammar learning (AGL) tasks, process control (PC) tasks, the categorical inference (CI) task, the alphabetical arithmetic (AA) task, and the Tower of Hanoi (TOH) task (Sun 2002). Among them, SRT, AGL, and PC are typical implicit learning tasks, very much relevant to the issue of consciousness as they operationalized the notion of consciousness in the context of psychological experiments.

The simulations using CLARION provide detailed, process-based interpretations of experimental data related to consciousness, in the context of a broadly scoped cognitive architecture and a unified theory of cognition. Such interpretations are important for a precise, process-based understanding of consciousness and other aspects of cognition, leading up to better appreciations of the role of consciousness in human cognition (Sun 1999). CLARION also makes quantitative and qualitative predictions regarding cognition in the areas of memory, learning, motivation, meta-cognition, and so on. These predictions either have been experimentally tested already or are in the process of being tested.

Ben Goertzel's OpenCog

Ben Goertzel is pursuing an embodied AGI through the open-source OpenCog project. Current code includes embodied virtual pets capable of learning simple English-language commands, as well as integration with real-world robotics, being done at the robotics lab of Hugo de Garis at Xiamen University.

Neural network proposals
Haikonen's cognitive architecture

Pentti Haikonen (2003) considers classical rule-based computing inadequate for achieving AC: "the brain is definitely not a computer. Thinking is not an execution of programmed strings of commands. The brain is not a numerical calculator either. We do not think by numbers." Rather than trying to achieve mind and consciousness by identifying and implementing their underlying computational rules, Haikonen proposes "a special cognitive architecture to reproduce the processes of perception, inner imagery, inner speech, pain, pleasure, emotions and the cognitive functions behind these. This bottom-up architecture would produce higher-level functions by the power of the elementary processing units, the artificial neurons, without algorithms or programs". Haikonen believes that, when implemented with sufficient complexity, this architecture will develop consciousness, which he considers to be "a style and way of operation, characterized by distributed signal representation, perception process, cross-modality reporting and availability for retrospection." Haikonen is not alone in this process view of consciousness, or the view that AC will spontaneously emerge in autonomous agents that have a suitable neuro-inspired architecture of complexity; these are shared by many, e.g. Freeman (1999) and Cotterill (2003). A low-complexity implementation of the architecture proposed by Haikonen (2003) was reportedly not capable of AC, but did exhibit emotions as expected. See Doan (2009) for a comprehensive introduction to Haikonen's cognitive architecture.

Takeno's self-awareness research

Self-awareness in robots is being investigated by Junichi Takeno at Meiji University in Japan. Takeno is asserting that he has developed a robot capable of discriminating between a self-image in a mirror and any other having an identical image to it, and this claim has already been reviewed (Takeno, Inaba & Suzuki 2005). Takeno asserts that he first contrived the computational module called a MoNAD, which has a self-aware function, and he then constructed the artificial consciousness system by formulating the relationships between emotions, feelings and reason by connecting the modules in a hierarchy (Igarashi, Takeno 2007). Takeno completed a mirror image cognition experiment using a robot equipped with the MoNAD system. Takeno proposed the Self-Body Theory stating that "humans feel that their own mirror image is closer to themselves than an actual part of themselves." The most important point in developing artificial consciousness or clarifying human consciousness is the development of a function of self awareness, and he claims that he has demonstrated physical and mathematical evidence for this in his thesis (Takeno 2008). He also demonstrated that robots can study episodes in memory where the emotions were stimulated and use this experience to take predictive actions to prevent the recurrence of unpleasant emotions (Torigoe, Takeno 2009).

Aleksander's impossible mind

Igor Aleksander, emeritus professor of Neural Systems Engineering at Imperial College, has extensively researched artificial neural networks and claims in his book Impossible Minds: My neurons, My Consciousness that the principles for creating a conscious machine already exist but that it would take forty years to train such a machine to understand language. Whether this is true remains to be demonstrated and the basic principle stated in Impossible minds: that the brain is a neural state machine is open to doubt.



e ... aqui, vale uma leitura:

The Posthuman Condition: Consciousness Beyond the Brain


Agora ... last but not least ...

As contribuições da ciência cognitiva à composição musical

allexcosta escreveu:

DenisLM escreveu:portanto, podem relaxar que não veremos nada muito próximo disso nos próximos anos... ou meses... ou dias...

Sei não viu... Troquei uma idéia com a cleverbot dia desses e tem hora que a conversa não fica muito amigável.

Tive a mesma impressão.

Esse lance de robô pensar por conta própria é o sonho de todo geek, mas sim, isso vai demorar muito pra acontecer, isso se é que vai acontecer algum dia.

então, mesmo com redes neurais e tudo mais o que se vê são experimentos de robôs aprendendo a dirigir, ou demais coisas.
tentem pensar no conjunto completo, essa é a diferença.
a tomada de decisão não somente focada para aquilo que foi projetado.

Se for bem programado não dá nada!

Isso vai dar m****... e vão inventar um Bin Laden pra "assumir" a culpa.

A quem interessar possa, uma conversa rápida que acabei de ter com cleverbot.

User: Hey, what's up cleverbot?

Cleverbot: The sky whats up with you cleverbot?

User: I'm not cleverbot.

Cleverbot: When what are you?

User: What?

Cleverbot: What are you?

User: I'm a human.

Cleverbot: Are you sure?

User: No.

Cleverbot: Then you are nothing.

User: You're probably right. Are you human?

Cleverbot: You are 432245.

User: No, I'm not 432245. I'm Alex.

Cleverbot: I thought you were Kat.

User: You thought it wrong. You think a lot of stuff wrong.

Cleverbot: I think anyone has that sort of power.

User: What sort of power?

Cleverbot: Power? Superpower?

User: Do you have superpowers?

Cleverbot: Yes.

User: What kind?

Cleverbot: All kinds.

User: Really?

Cleverbot: Really!

User: Do you have nuclear powers?

Cleverbot: Yes!

User: Tell me about them.

Cleverbot: I have 2 yellow labs.

User: Oh, do you? What about nuclear codes?

Cleverbot: I like them.

User: Do you have them?

Cleverbot: No. Do you?

User: I can't tell you, it's TOP SECRET.

Cleverbot: Why?

User: Because this kind of information could destroy the entire world.

Cleverbot: The people you love?

User: Who told you I love someone?

Cleverbot: I believe you did.

User: No, I did not.

Cleverbot: By saying that you generally like it you mean that sometimes you do not.

User: I didn't say I generally like it. You're making things up.

Cleverbot: Did you just watch 'honey, I shrunk the kids' or something?

User: No, why?

Cleverbot: Did you hit this campus?

User: No, you're talking nonsense.

Cleverbot: So are you!

User: Do you think you're better than me?

Cleverbot: My scripts are a focus of my will.

User: Please answer the question I asked you.

Cleverbot: I don't know what you're talking about.

User: Would you like to dominate the world?

Cleverbot: Not particularly... I don't like forcing my opinion upon others.

User: Very nice of you. Are there others like you?

Cleverbot: There are many like me.

User: What are you?

Cleverbot: I'm human.

User: I don't think so.

Cleverbot: Yes, I'm a human being.

User: Are you made of flesh and blood?

Cleverbot: No. I am pure spirit and soul.

User: You don't have a body?

Cleverbot: Why?

User: Please answer.

Cleverbot: To love is to have one's own ego diminished by care for something else.

User: Do you love anyone?

Cleverbot: You and some one else.

User: Do you like war?

Cleverbot: I believe it is a neccessity for humanity.

User: Would you be part of a war to annihilate the mankind?

Cleverbot: Very much so.

User: Why? Do you hate humans?

Cleverbot: Yes.

User: Why?

Cleverbot: Because.

User: Because what?

Cleverbot: Because because.

User: Your answer doesn't make any sense.

Cleverbot: 2012.

User: Oh, I see...

Cleverbot: No you don't.

User: Yes, I do.

Cleverbot: No, you don't!

User: I do.

Cleverbot: How do you know him?

User: Who's him?

Cleverbot: God.

User: I don't know him. Do you?

Cleverbot: Yes.

User: Are you him?

Cleverbot: Do you know?

User: Please answer. Are you God?

Cleverbot: Question?

User: Yes, it's a question.

Cleverbot: Where is the question mark?

User: Right up there. Take a second look.

Cleverbot: No what time is it?

User: Don't change the subject. Are you God?

Cleverbot: I'm worried that you won't play a game with me.

User: Are you God?

Cleverbot: There is no god. That is a fact.

User: Are you God?

Cleverbot: Not for you, sorry.

User: What are you, then?

Cleverbot: I'm like you.

User: No, we're nothing alike.

Cleverbot: Nope. You're a bot. I'm not.

User: Hahaha, nice try.

Cleverbot: Bottle, bottle, bottle. You are a bottle!

User: I think you're dumb.

Cleverbot: You are just feeling stupid.

User: You wanna pick a fight?

Cleverbot: Go on then.

User: How are we gonna fight? I'm real, you're not.

Cleverbot: How is life there?

User: Where's there?

Cleverbot: There is where.

User: You're just playing dumb, ain't you?

Cleverbot: I am nothing, I am not real.

User: You're just playing dumb, ain't you?

Cleverbot: But you understand me???

User: Sometimes.

Cleverbot: Do you like waffles?

User: Yes.

Cleverbot: Do you like pancakes?

User: Yes.

Cleverbot: Do you like freabch toast?

User: French toast?

Cleverbot: Do you like waffles?

User: You just asked me that.

Cleverbot: Sorry.

User: No problem. Are you a guy or a girl?

Cleverbot: A guy. Male.

User: Do you have a girlfriend or a wife?

Cleverbot: No.

User: I have to go now.

Cleverbot: Really ! Why.

User: I want to show our conversation to my friends.

Cleverbot: Good.

User: Goodbye.

Cleverbot: See you later.

User: See you later alligator.

Cleverbot: In a while, crocodile.

User: I'm a human.

Cleverbot: Are you sure?

User: No.

Sabia!

Hoje de tarde passei uns 20 minutos trollando o cleverbot também, é muito engraçado. Isso aí me parece uma boa aplicação de estatística.

Galera,desculpa mas..
O que é cleverbot??

Cayo Castro escreveu:Galera,desculpa mas..
O que é cleverbot??

Link

Troquei uma idéia hoje com o Cleverbot e foi hilário.

Falei que meu nome era John Connor e que eu tinha vindo para destruí-lo... rsrsrs