Questions tagged [ai-safety]

For questions regarding various parameters/methods of implementation/improvement/analyzing the safety of an Artificially Intelligent algorithm. A typical real world example is autonomous vehicles.

Filter by
Sorted by
Tagged with
30
votes
9answers
5k views

Is artificial intelligence vulnerable to hacking?

The paper The Limitations of Deep Learning in Adversarial Settings explores how neural networks might be corrupted by an attacker who can manipulate the data set that the neural network trains with. ...
9
votes
1answer
394 views

What tools are used to deal with adversarial examples problem?

The problem of adversarial examples is known to be critical for neural networks. For example, an image classifier can be manipulated by additively superimposing a different low amplitude image to each ...
6
votes
3answers
680 views

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

Do we know why Tesla's autopilot mistaken empty sky with a high-sided lorry which resulted in fatal crash involving a car in self-drive mode? Was it AI fault or something else? Is there any technical ...
5
votes
3answers
403 views

Can artificial intelligence applications be hacked? [duplicate]

Can artificial intelligence (or machine learning) applications or agents be hacked, given that they are software applications, or are all AI applications secure?
5
votes
1answer
264 views

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

I was wondering what will happen when somebody places a fake speedsign, of 10 miles per hour on a high way. Will a autonomous car slow down? Is this a current issue of autonomous cars?
5
votes
1answer
60 views

What is the relationship between robustness and adversarial machine learning?

I have been reading a lot of articles on adversarial machine learning and there are mentions of "best practices for robust machine learning". A specific example of this would be when there are ...
4
votes
2answers
225 views

Concrete examples of unintentional adversarial AI behaviour

Are there any real-world examples of unintentional "bad" AI behaviour? I'm not looking for hypothetical arguments of malicious AI (AI in a box, paperclip maximizer), but for actual instances in ...
4
votes
1answer
181 views

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

I understand that AI researchers are trying to create AI designs that allow for desired behavior without undesirable side-effects. A classic example of an attempt is Isaac Asimov's "Three Laws of ...
4
votes
1answer
59 views

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

Nowadays we don't know how to create AI in a safe way (I think that we don't even know yet how to define a safe AI), but there is a lot of research in developing a model allowing it. Let's say, that ...
4
votes
1answer
107 views

What topologies support recognition of action sequences?

The ability to recognize an object with particular identifying features from single or multiple camera shoots with the temporal dimension digitized as frames has been shown. The proof is that the ...
3
votes
3answers
164 views

Legal compliance and AI auditing framework

Providing that more and more decisions about human life are (to be) decided by machine (like access to loans, housing, scholarship, jobs, healthcare, insurance, etc.) at the same time, in many ...
3
votes
4answers
518 views

Can an evolving AI be programmed not to lie?

It seems that certain AI are able to lie or deceive. See e.g. Evolving Robots Learn To Lie To Each Other (Popsci), Robots Evolve to Deceive (MIT Tech Review) or Robots 'Evolve' the Ability to Deceive (...
2
votes
0answers
71 views

Does Rice's theorem prove safe AI is undecidable?

According to Wikipedia In computability theory, Rice's theorem states that all non-trivial, semantic properties of programs are undecidable. A semantic property is one about the program's ...
1
vote
2answers
169 views

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

If the AI goal is to serve humans and protect them (if this ever happens) and AI someday realizes that humans destroy themselves, will it try to control people for their own good, that is, will it ...
1
vote
0answers
22 views

To what level of abstraction must fully automated vehicles build their driving model before safety can be maximized?

There are several levels of abstraction involved in piloting and driving. Signals representing the state of the vehicle and its environment originating from multiple transducers1 Latched sample ...
0
votes
1answer
65 views

Does this prove AI Safety is undecidable?

Does this prove AI Safety is undecidable? Proof: Output meaning output to computer program. [A1] Assume we have a program that decides which outputs are “safe”. [A2] Assume we have an example of ...