A backdoor watermarking scheme for object detectors that poisons bounding-box coordinates in API responses, enabling near-perfect detection of extracted models in several settings.
Clean-image backdoor: Attacking multi- label models with poisoned labels only
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors
A backdoor watermarking scheme for object detectors that poisons bounding-box coordinates in API responses, enabling near-perfect detection of extracted models in several settings.