Adversarial Examples That Fool Both Computer Vision And Time-Limited Humans

Authors:
Gamaleldin Elsayed Google Brain
Shreya Shankar Stanford University
Brian Cheung UC Berkeley
Nicolas Papernot Google Brain
Alexey Kurakin Google Brain
Ian Goodfellow Google
Jascha Sohl-Dickstein Google Brain

Introduction:

Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich.

Abstract:

Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recent techniques that transfer adversarial examples from computer vision models with known parameters and architecture to other models with unknown parameters and architecture, and by matching the initial processing of the human visual system. We find that adversarial examples that strongly transfer across computer vision models influence the classifications made by time-limited human observers.

You may want to know: