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.
Deep learning and medical diagnosis: A review of literature.Multimodal Technologies and Interaction, 2(3):47
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.