FRA-Attack uses high-pass DCT feature alignment and frequency-domain gradient regularization to boost adversarial transferability across 15 MLLMs from 7 vendors.
On evaluating adversarial robustness of large vision-language models.Advances in Neural Information Processing Systems, 36:54111–54138
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.