Backdoor poisoning triggers in contrastive learning can be repurposed as statistical watermarks for dataset IP protection via a multi-level scheme and density-based verification.
Entropymark: Towards more harm- less backdoor watermark via entropy-based constraint for open-source dataset copyright protection,
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
-
Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning
Backdoor poisoning triggers in contrastive learning can be repurposed as statistical watermarks for dataset IP protection via a multi-level scheme and density-based verification.