Enlarge /. Artistic representation of the opposing AI as controversial.
Grassetto / Getty Images
In the third and final installation of our podcast mini-series on artificial intelligence, created in collaboration with Darktrace, we deal with the field of AI-fighting AI – or what researchers call "controversial AI".
Contradictory artificial intelligence can take many forms – for example, as a tool for hacking through AI-based security of other systems or to deceive another algorithm with inputs that cause a specific, incorrect result. Ars editors Sean Gallagher and Lee Hutchinson spoke to ForAllSecure's CEO, Defense Advanced Research Projects Agency 2016 Cyber Grand Challenge winning team David Brumley, about progress in AI-driven hacking. Lujo Bauer, professor of electrical and computer engineering at the Institute for Software Research in Carnegie Mellon, spoke to Lee and Sean about his research into using AI to combat technologies such as facial recognition. And Max Heinemeyer, director of threat hunting at Darktrace, has already been discussing research into how AI-controlled attacks on computer networks can be stopped.
This special edition of the Ars Technicast podcast is available at the following locations:
iTunes:
https://itunes.apple.com/us/podcast/the-ars-technicast/id522504024?mt=2 (It may take a few hours for the publication to appear.)
RSS:
http://arstechnica.libsyn.com/rss
Stitcher
http://www.stitcher.com/podcast/ars-technicast/the-ars-technicast
Libsyn:
http://directory.libsyn.com/shows/view/id/arstechnica