ErrolSignal

OpenAI Blog · May 3, 2019

Transfer of adversarial robustness between perturbation types

Reviewed by Errol Vogt, Site support technician & online learning analyst · original summary · editorial policy

Transfer of adversarial robustness between perturbation types. Source details are limited, so this entry summarizes the headline change only for operators tracking their tools.

Operator takeaway: For operators: review whether 'Transfer of adversarial robustness between perturbation types' affects your current setup before relying on it in production.

Read the original at OpenAI Blog →

← All updates