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.
Pushing the frontier of black-box lvlm attacks via fine-grained detail targeting
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
FRA-Attack uses high-pass DCT feature alignment and frequency-domain gradient regularization to boost adversarial transferability across 15 MLLMs from 7 vendors.
citing papers explorer
-
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.
-
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
FRA-Attack uses high-pass DCT feature alignment and frequency-domain gradient regularization to boost adversarial transferability across 15 MLLMs from 7 vendors.