21 votes

Is artificial intelligence vulnerable to hacking?

AI is vulnerable from two security perspectives the way I see it: The classic method of exploiting outright programmatic errors to achieve some sort of code execution on the machine that is running ...
12 votes
Accepted

Are Asimov's Laws flawed by design, or are they feasible in practice?

Asimov's laws are not strong enough to be used in practice. Strength isn't even a consideration, when considering that since they're written in English words would first have to be interpreted ...
  • 1,345
7 votes

Is artificial intelligence vulnerable to hacking?

Programmer vs Programmer It's a "infinity war": Programmers vs Programmers. All thing can be hackable. Prevention is linked to the level of knowledge of the professional in charge of security and ...
6 votes
Accepted

What will happen when you place a fake speedsign on a highway?

https://www.technologyreview.com/s/530276/hidden-obstacles-for-googles-self-driving-cars/ Google’s cars can detect and respond to stop signs that aren't on its map, a feature that was introduced to ...
  • 259
6 votes

Is artificial intelligence vulnerable to hacking?

How we can prevent it? There are several works about AI verification. Automatic verifiers can prove the robustness properties of neural networks. It means that if the input X of the NN is perturbed ...
5 votes
Accepted

Why is AI safety so much harder than Isaac Asimov's "Three Laws of Robotics"?

The reason this is hard is because it is not trivial to understand what a law means. Many humans still have a hard time understanding laws and thus we have millions of judges and lawyers who study ...
5 votes

Concrete examples of unintentional adversarial AI behaviour

There is the case of the tesla accident where the car was in autopilot and crashed into a truck because it appears the vehicle mistook a lightly coloured truck for the sky, killing the driver: https://...
  • 291
5 votes

Why does Stephen Hawking say "Artificial Intelligence will kill us all"?

It's not just Hawking, you hear variations on this refrain from a lot of people. And given that they're mostly very smart, well educated, well informed people (Elon Musk is another, for example), it ...
  • 3,697
5 votes

Can artificial intelligence applications be hacked?

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 ...
4 votes
Accepted

What tools are used to deal with adversarial examples problem?

However, do industrial strength, production ready defensive strategies and approaches exist? Are there known examples of applied adversarial-resistant networks for one or more specific types (e.g. for ...
  • 9,604
4 votes

Is artificial intelligence vulnerable to hacking?

Is Artificial Intelligence Vulnerable to Hacking? Invert your question for a moment and think: What would make AI at less of a risk of hacking compared to any other kind of software? At the end ...
  • 210
4 votes

Is artificial intelligence vulnerable to hacking?

I believe it is, no system is safe, however I am not sure if I can still say this after 20-30 years of AI development/evolution. Anyways, there are articles that showed humans fooling AI (Computer ...
  • 41
4 votes

Why does Stephen Hawking say "Artificial Intelligence will kill us all"?

As Andrew Ng said, worrying about such threat from AI is like worrying about of overpopulation on Mars. It is science fiction. That being said, given the rise of (much weaker) robots and other (semi-...
4 votes

Why does Stephen Hawking say "Artificial Intelligence will kill us all"?

Because he did not yet know how far away current AI is... Working in an media AI lab, I get this question a lot. But really... we are still a long way from this. The robots still do everything we ...
  • 204
4 votes
Accepted

Why did a Tesla car mistake a truck with a bright sky?

Tesla's technology is assistive, as Alexey points out, so this is not a case of an autonomous system (e.g. an AGI) doing some fatal stunt (the product name AutoPilot is famously misleading). Now on ...
  • 1,490
4 votes

Concrete examples of unintentional adversarial AI behaviour

The infamous Flash Crash of 2010 may qualify. It didn't involve Artificial General Intelligence (which is still a hypothetical) or even "strong narrow AI" (such as AlphaGo) but does involve ...
  • 6,107
4 votes
Accepted

What is the relationship between robustness and adversarial machine learning?

A robust ML model is one that captures patterns that generalize well in the face of the kinds of small changes that humans expect to see in the real world. A robust model is one that generalizes ...
3 votes

What are examples of techniques to prevent bias in artificial intelligence systems?

It's important to note that, ultimately, the statistical methods we currently use in ML research are just that: statistical methods. So, when they show some "bad behaviour", it's not because ...
3 votes

Why did a Tesla car mistake a truck with a bright sky?

As far as I know, Tesla cars autopilot is not a 100% AI pilot, it's an assitant: as it detects hands off wheel it slows down, so it's incorrect to speak about AI mistake: it is not trained/designed to ...
3 votes

Why does Stephen Hawking say "Artificial Intelligence will kill us all"?

To put it simply in layman terms, what are the possible threats from AI? Currently, there are no threat. The threat comes if humans create a so-called ultraintelligent machine, a machine that can ...
  • 1,481
3 votes

Why does Stephen Hawking say "Artificial Intelligence will kill us all"?

There are a number of long resources to answer this sort of question: consider Stuart Armstrong's book Smarter Than Us, Nick Bostrom's book Superintelligence, which grew out of this edge.org answer, ...
3 votes
Accepted

Why are AI Safety discussions almost always from the perspective of reinforcement learning?

I think what you are really asking is why don't we talk about alignment from the perspective of general deep learning? In fact, we do talk about alignment for general AI system that's being used in ...
2 votes

Why does Stephen Hawking say "Artificial Intelligence will kill us all"?

He says this because it can happen. If something becomes smarter than us, why would it continue to serve us? The worst case scenario is that it takes over all manufacturing processes and consumes all ...
  • 129
2 votes
Accepted

Does this prove AI Safety is undecidable?

You are essentially correct, although there may be some minor holes in the structure of your argument specifically. But if we're speaking informally, yes, you are correct. This is a consequence of ...
  • 136
1 vote

If the AI goal is the protection of humans, will it always pursue this goal?

If the AI is static (heuristic and fixed), it will always pursue the stated goal. However, such a system would be "brittle", and either break or produce bad output if confronted with input not ...
  • 6,107
1 vote

If the AI goal is the protection of humans, will it always pursue this goal?

If the main goal of AI (which I assume you mean an AGI) is to protect humans and AI will be effective, then AI will always attempt to pursue its main goal (otherwise the assumption of its ...
  • 35.6k
1 vote

Where are reinforcement algorithms used in financial services?

I know the new bot in JP Morgan uses reinforcement learning: Machine Learning in FX There a lot of studies of Reinforcement learning can apply in crypto currency trading. Here is one of many examples: ...
1 vote

Can artificial intelligence applications be hacked?

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 ...
1 vote

Is it necessarry to create theory/infrastructure to prevent people from creating AI incompatible with a safe model (if we create one)?

It seems impossible to prevent that. If someone can make a safe AI from scratch in the near future, then someone else can make a dangerous AI from scratch as well. If all that's needed is a computer (...
1 vote

What topologies support recognition of action sequences?

This is an old area of AI called "Plan Recognition", which has about 3.5 million results in Google Scholar. A lot of the modern work is done with classical search techniques coupled with expert ...

Only top scored, non community-wiki answers of a minimum length are eligible