trends.barnas.net

method · first seen 31 Oct 2026

adversarial perturbation attack

Attack that adds crafted small input or activation perturbations to make a model behave incorrectly while evading detection.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

distributed inferenceverifiable computation