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.
A survey on self-supervised learning: Algorithms, applications, and future trends
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
ArmSSL is a black-box verifiable and adversarially robust watermarking framework for SSL pre-trained encoders using paired discrepancy enlargement, latent entanglement, distribution alignment, and reference-guided tuning.
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.
-
ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
ArmSSL is a black-box verifiable and adversarially robust watermarking framework for SSL pre-trained encoders using paired discrepancy enlargement, latent entanglement, distribution alignment, and reference-guided tuning.