News for hackers. Stuff that matters.
Re:Adversarial Examples That Fool Both Computer Vision and T... by jon_richards on Monday November 12, 2018 @02:40AM (#18431146)
As xkcd points out, you don't have to worry too much about people trying to trick self-driving systems with visual hacks.

https://xkcd.com/1958/

Re:Adversarial Examples That Fool Both Computer Vision and T... by menudo on Monday November 12, 2018 @10:10AM (#18433012)
The XKCD comic strip makes for a useful and shallow zinger, amid casual banter, but the real world actually faces two or three new layers of complexity, which actually reassert the problem it attempts to dispose of.

1. The global reach of networked telecommunications permits a small quantity of sociopathic murderers to operate from beyond jurisdictions that can reach them, and also assists in destroying evidence of their interference.

2. Computational power enables force multiplication, such that even just one sociopathic murderer could exploit software flaws across millions of vehicles, simultaneously.

3. Some software exploits will work against self driving cars, which could never work against an ordinary person, and of course, vice versa, but not so much via remote control at a distance, when people are the operators, while we still lack electronic interfaces to our central nervous system.

Re:Adversarial Examples That Fool Both Computer Vision and T... by jon_richards on Monday November 12, 2018 @10:22PM (#18438235)
>visual hacks

We were discussing "tricking" the computer vision component of a self-driving car, not getting software access. That's still a concern, but it's an entirely different set of security requirements that we already face in planes and existing cars.

Re:Adversarial Examples That Fool Both Computer Vision and T... by menudo on Tuesday November 13, 2018 @08:19AM (#18440695)
Except XKCD wasn't.
Re:Adversarial Examples That Fool Both Computer Vision and T... by jon_richards on Tuesday November 13, 2018 @11:13PM (#18447427)
To me,

>painting fake lines on the road, or dropping a cutout of a pedestrian onto a highway

sounds like

>"tricking" the computer vision component of a self-driving car, not getting software access.

Re:Adversarial Examples That Fool Both Computer Vision and T... by carlmr on Monday November 12, 2018 @05:12AM (#18431639)
Ok, fair point about the hacking, but unintentionally misleading things are also hard to estimate.