OpenAI Blog · Jul 17, 2017
Robust adversarial inputs
Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy
Robust adversarial inputs. 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. This update is relevant for small-office operators tracking changes in their tools.
Operator takeaway: For operators: review whether 'Robust adversarial inputs' affects your current setup before relying on it in production.
ai