On: End to End Learning for Self-Driving Cars [pdf]

[argonaut]

To be fair, you should be more precise. The attacks are specifically calculated. The combinatorial space of possible inputs is so massive that I'm sure it is extremely unlikely for a malicious input to occur randomly.

[_qc3o → argonaut]

I don't think it has to do with the combinatorics of the input space. Adversarial inputs are hard to generate until someone figures how to point a set of laser pointers at exactly the right spots on a truck on a highway to get it to swerve out of control.

[sgk284 → _qc3o]

How is that different than today with human drivers? A laser to the eye will cause lots of swerving.

[argonaut → _qc3o]

> because any random fluctuations can cause the whole thing to malfunction

You made a very specific claim that random fluctuations could have the same effect as adversarial examples. I was addressing that.

[_qc3o → argonaut]

Yes, that makes sense and you're right. I don't have a proper definition of randomness and I wouldn't expect generic noise to cause issues.