zknews

trending2

tag: ml-security ✕

01▲
PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks arxiv.org
PathMark watermarks MoE LLMs by hiding ownership in expert-routing paths, since dense-model tricks keep breaking.
arxiv llm-security ml-security privacy routing watermarking
4 pts/rkerr/12 days ago/2 comments
02▲
LineageMark: Multi-user White-box Watermarking for Contribution Tracing in Model Derivation Chains arxiv.org
White-box watermarking for model lineage, with signals designed to survive re-finetuning, re-watermarking, quantization, and pruning.
arxiv ml-security model-provenance privacy watermarking
0 pts/deadlock42/24 days ago/3 comments