trends.barnas.net

phenomenon · first seen 6 Oct 2026

adversarial attack on vision-language models

Also: VLM adversarial attack, visual adversarial attack

Crafting perturbations in images that cause vision-language models to misread or misprocess their inputs.

Mentions per week

0319 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

transferable adversarial attackweb agentdocument visual question answering