On Distinctive Properties of Universal Perturbations
CoRR(2021)
Abstract
We identify properties of universal adversarial perturbations (UAPs) that distinguish them from standard adversarial perturbations. Specifically, we show that targeted UAPs generated by projected gradient descent exhibit two human-aligned properties: semantic locality and spatial invariance, which standard targeted adversarial perturbations lack. We also demonstrate that UAPs contain significantly less signal for generalization than standard adversarial perturbations -- that is, UAPs leverage non-robust features to a smaller extent than standard adversarial perturbations.
MoreTranslated text
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined