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

Attacks from adversarial machine learning (ML) have the potential to be used"for good": they can be used to run counter to the existing power structureswithin ML, creating breathing space for those who would otherwise be thetargets of surveillance and control. But most research on adversarial ML hasnot engaged in developing tools for resistance against ML systems. Why? In thispaper, we review the broader impact statements that adversarial ML researcherswrote as part of their NeurIPS 2020 papers and assess the assumptions thatauthors have about the goals of their work. We also collect information abouthow authors view their work's impact more generally. We find that mostadversarial ML researchers at NeurIPS hold two fundamental assumptions thatwill make it difficult for them to consider socially beneficial uses ofattacks: (1) it is desirable to make systems robust, independent of context,and (2) attackers of systems are normatively bad and defenders of systems arenormatively good. That is, despite their expressed and supposed neutrality,most adversarial ML researchers believe that the goal of their work is tosecure systems, making it difficult to conceptualize and build tools fordisrupting the status quo.

Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks