An attacker with one seed image per class can steal a black-box image classifier by genetically evolving text prompts, guided only by the victim's hard-label predictions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stealix: Model Stealing via Prompt Evolution
An attacker with one seed image per class can steal a black-box image classifier by genetically evolving text prompts, guided only by the victim's hard-label predictions.