Ars Technicast exclusive version, component 3: Putting AI to do the job defending your things

Artist's impression of adversarial AI being adversarial.

Enlarge / Artist’s effect of adversarial AI staying adversarial. (credit history: Grassetto / Getty Photos)

In the third and remaining installation of our podcast miniseries on synthetic intelligence, developed in association with Darktrace, we delve into the realm of AI battling AI—or what scientists refer to as “adversarial AI.”

Adversarial synthetic intelligence can take many forms—as a instrument for hacking by way of AI-powered security of other techniques, for illustration, or deceiving a further algorithm with enter that brings about a specific, bogus result. Ars editors Sean Gallagher and Lee Hutchinson spoke with the leader of the successful staff from the 2016 Defense Innovative Analysis Jobs Agency’s Cyber Grand Challenge, ForAllSecure CEO David Brumley, about progress in AI-driven hacking. Lujo Bauer, a professor of electrical and computer system engineering at the Institute for Software program Study at Carnegie Mellon, joined Lee and Sean to speak about his exploration into techniques to use AI to defeat technologies these as facial recognition. And Max Heinemeyer, director of threat hunting at Darktrace, talked over investigate presently remaining finished into how to stop AI-pushed attacks on computer system networks.

This particular edition of the Ars Technicast podcast can be accessed in the next areas:

Browse 4 remaining paragraphs | Feedback

Supply backlink


Don't worry we don't spam

We will be happy to hear your thoughts

      Leave a reply

      Enable registration in settings - general