shipfeedAI news, curated daily

23:52:26 CET
20 MAY23:52:26shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Robust adversarial inputs

OpenAI publishes adversarial images that reliably fool neural network classifiers across varied scales and perspectives, countering claims that multi-angle capture makes self-driving car vision systems hard to deceive.

Jul 17 · · primary fetch1 sourceupdated Jul 17 ·

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comRobust adversarial inputsprimary