Visual prompting exposes a class subspace inconsistency in backdoored models, and BPROM uses prompted confidence vectors to detect hidden backdoors in black-box models with AUROC often at 1.0.
• Poison rate: The proportion of training data with the trigger pattern
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Prompting the Unseen: Detecting Hidden Backdoors in Black-Box Models
Visual prompting exposes a class subspace inconsistency in backdoored models, and BPROM uses prompted confidence vectors to detect hidden backdoors in black-box models with AUROC often at 1.0.