Pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.AI 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Universal Adversarial Attack on Aligned Multimodal LLMs

cs.AI · 2025-02-11 · conditional · novelty 4.0

A single optimized image, trained through the vision and language modules, makes aligned multimodal LLMs produce dangerous responses across diverse prompts and some models.

citing papers explorer

Showing 1 of 1 citing paper.

  • Universal Adversarial Attack on Aligned Multimodal LLMs cs.AI · 2025-02-11 · conditional · none · ref 6

    A single optimized image, trained through the vision and language modules, makes aligned multimodal LLMs produce dangerous responses across diverse prompts and some models.