digest

6 Results / Page 1 of 1

todayNovember 30, 2019

  • 75
close

Adversarial ML admin

The Greater Good: using AI for public safety

Most uses for AI are not flashy or glamorous: there is rarely a Jarvis ready to prepare an iron suit. Instead, scientists are working on airport security systems, tempering with protest headcounts, sensitive content flagging, etc.  —  mundane systems that keep millions of people safe. Maybe, AI is a little ...

todayApril 30, 2019

  • 97
close

Adversarial ML admin

Hidden in Plain Sight: Attacks that Make Us Invisible

In April we fool. We fool visual classifiers and speech recognition systems with stickers, print outs, and imperceptible commands. Here is a rundown of the most impressive (and terrifying) ways the researchers attacked ML models in April 2019. Fooling automated surveillance cameras: adversarial patches to attack person detection Belgian students ...