English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper substantially extends our work published at ECCV, in which anintermediate-level attack was proposed to improve the transferability of somebaseline adversarial examples. Specifically, we advocate a framework in which adirect linear mapping from the intermediate-level discrepancies (betweenadversarial features and benign features) to prediction loss of the adversarialexample is established. By delving deep into the core components of such aframework, we show that 1) a variety of linear regression models can all beconsidered in order to establish the mapping, 2) the magnitude of the finallyobtained intermediate-level adversarial discrepancy is correlated with thetransferability, 3) further boost of the performance can be achieved byperforming multiple runs of the baseline attack with random initialization. Inaddition, by leveraging these findings, we achieve new state-of-the-arts ontransfer-based $\ell_\infty$ and $\ell_2$ attacks. Our code is publiclyavailable at https://github.com/qizhangli/ila-plus-plus-lr.

An Intermediate-level Attack Framework on The Basis of Linear Regression