Synthetic images from diffusion model APIs can train substitute models that extract black-box classifiers and enable high-success adversarial transfer attacks with 0.01x the query budget of prior methods.
We developed a method for training robust substitute models in a data-free, hard-label, and query-limited setting
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Explore the vulnerability of black-box models via diffusion models
Synthetic images from diffusion model APIs can train substitute models that extract black-box classifiers and enable high-success adversarial transfer attacks with 0.01x the query budget of prior methods.