Mosaic combines text perturbation, multi-view image optimization, and surrogate model ensembles to reduce reliance on any single open-source model and achieve higher attack success rates on commercial closed-source VLMs.
A frustratingly simple yet highly effective attack baseline: Over 90% success rate against the strong black-box models of gpt-4.5/4o/o1
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
baseline 1polarities
baseline 1representative citing papers
DarkLLM trains an LLM to generate language-driven adversarial perturbations that unify targeted, untargeted, segmentation, and multi-model attacks on foundation models.
PRAF-Attack improves targeted attack transferability on black-box MLLMs by using multi-scale progressive resolution and adaptive intermediate feature alignment instead of final-layer global features.
citing papers explorer
-
Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization
Mosaic combines text perturbation, multi-view image optimization, and surrogate model ensembles to reduce reliance on any single open-source model and achieve higher attack success rates on commercial closed-source VLMs.
-
DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models
DarkLLM trains an LLM to generate language-driven adversarial perturbations that unify targeted, untargeted, segmentation, and multi-model attacks on foundation models.
-
Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment
PRAF-Attack improves targeted attack transferability on black-box MLLMs by using multi-scale progressive resolution and adaptive intermediate feature alignment instead of final-layer global features.