conftrace_

backdoor watermarking

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

loss masking (1) semantic perturbation (1) backdoor watermark (1) semantic perturbation attack (1) embedding watermark (1) memorization prevention (1) watermark verification (1) targeted poisoning (1) dataset ownership (1) large language model (1)

Papers

Data Taggants: Dataset Ownership Verification Via Harmless Targeted Data Poisoning ICLR 2025 Empirical Evaluation of Loss Masking to Selectively Prevent Memorization ACL 2025 Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark EMNLP 2025 FedGMark: Certifiably Robust Watermarking for Federated Graph Learning NeurIPS 2024