Attacking Artificial Intelligence: How To Trick The Enemy

[rangerrebew]

 Attacking Artificial Intelligence: How To Trick The Enemy

“Autonomy may look like an Achilles’ heel, and in a lot of ways it is” – but for both sides, DTRA's Nick Wager said. “I think that’s as much opportunity as that is vulnerability. We are good at this… and we can be better than the threat.”

By Sydney J. Freedberg Jr. on February 06, 2019 at 5:37 PM
 

Maybe the Terminators should be afraid of us.

ARLINGTON: With the US, Russia, and China all investing in Artificial Intelligence for their armed forces, people often worry the Terminator is going to come to life and kill them. But given the glaring vulnerabilities of AI, maybe the Terminator ought to be afraid of us.

“People are saying, ‘oh my god, autonomy’s coming, Arnold is going to be here, he’s going to be out on the battlefield on the other side,’” said Marine rifleman turned AI expert Mike Kramer. ”I don’t believe that. This is an attack surface.”

https://breakingdefense.com/2019/02/attacking-artificial-intelligence-how-to-trick-the-enemy/

[bigheadfred]

Adding this link to another thread.