4
$\begingroup$

Can artificial intelligence be hacked or not by using enough computing skills or by other cryptography methods? So are we able to say that AI is one of in its secured form?

$\endgroup$
  • 2
    $\begingroup$ what do you mean by 'hacked' ? control it ? alter its 'behavior' ? and what do you mean by AI ? an AGI ? $\endgroup$ – Jérémy Blain Oct 24 '18 at 7:26
  • $\begingroup$ AI is short form of artificial intelligence which i use in question body while explaining and and hacked is basically linked with hacking meaning and the question which i asked in here is because of the reason that i want a brief discription that can i say that artifical intelligence is in its secured formed and no hacking can be done in here as artificial intelligence is a part of intelligence now $\endgroup$ – ME. Oct 24 '18 at 7:46
  • $\begingroup$ @Jérémy Blain Hope i make my question clear now? $\endgroup$ – ME. Oct 24 '18 at 7:49
  • $\begingroup$ absolutly not!! you don't seem to understand how AI is a broad term. what type of AI are you talking about ? Are you talking about the AI on your cellphone like Siri, the AI on google image that search for images linked to your keyword ? about an AI like terminator or I-robot ? more intelligence than human ? AI means so many things that it tells nothing at the same time.... I can say the same about hacking. Do you want to control the AI ? change its predictions ? make it doing other things ? Take it down ?? $\endgroup$ – Jérémy Blain Oct 24 '18 at 8:10
  • 1
    $\begingroup$ I can't ask the question myself as I am not in your head and I don't clearly know what you are asking. As I said, AI is broad, even on your cellphone. Cellphone is FULL of AI application. The AI controlling your battery, assistant, AI that control your screen brightness and so on. BE SPECIFIC about what hacking you're talking about, on what AI ? Is it to fool Siri and make it wrongly answer question, for example ? This is clear. Not your question. $\endgroup$ – Jérémy Blain Oct 24 '18 at 8:52
5
$\begingroup$

To answer your question, it really depends on the purpose of the Artificial Intelligence program.

For example, 4Chan has hacked a number of "Artificial Intelligent" bots, most notably was Microsoft's Twitter bot Tay. The general purpose of the bot was to parse what was tweeted at it and respond in kind, learning and evolving with each and every interaction.

Within 24 hours, 4Chan had corrupted Tay beyond repair, by teaching it racist and sexist terminology, ironic memes, sending it to shitpost tweets, and otherwise attempting to alter its output so much so that Microsoft had to remove it.

Now, the flaw with Tay was that it accepted any input, and learned off of that exclusively, without any interaction from the developers. Other bots have similar features, but they have checks in place that require human intervention to determine what is "quality" information to learn, and what is "bad" information to learn as to not pollute the global knowledge base of the bot.

These are just two examples of how Artificial Intelligence can be "hacked", but it ultimately comes down to how the programs are implemented.

You mention in one of your comments about Cellphone Artificial Intelligence such as Siri, and whether this technology can be hacked. The answer is - not really.

Siri learns based off of her global interactions - with limited user input allowed. You can ask Siri how to pronounce a name. When she pronounces it incorrectly, you can say to her "Siri that's now how you pronounce that". And she will provide you with a limited set of options of how you pronounce that name, and you have to choose which option sounds the best.

There was no option to allow a user to give Siri "bad" information, as she already populates the results for you, and you have to teach her based off of her list of options. To give Siri bad input, you would have to have access to Siri's global learning base, which we do not have access to, and alter how she accepts human interactions within the program - which would never happen due to too many moving parts within the iPhone update process, and would be caught before you were able to deploy your update.

$\endgroup$
  • 1
    $\begingroup$ Nice angle. I was going to post: "One way to 'hack' a learning algorithm would be to feed it bad data." $\endgroup$ – DukeZhou Oct 24 '18 at 20:03
1
$\begingroup$

Everything can be hacked. The solutions found by artificial intelligence can be much more efficient than human solutions, but they can also be confused because of the diversity and immensity of details that our mind possesses.

Artificial Intelligence models bring us more secure solutions, but nothing is 100% safe when we talk about information security. There are ways to improve security, hinder invasions and attacks, but every system has flaws.

Perhaps, in the future (things of my imagination) we will have an artificial superintelligence ahead of the human, which may be one of the greatest challenges of invasion of history, but until then .. just my imagination.

$\endgroup$
1
$\begingroup$

Perhaps what you are looking for is the notion of adversarial attacks on machine learning systems?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.