Nils Lukas, Tameem Bakr, Anish Ambreth
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
In federated learning (FL), K clients jointly train a model without sharing raw data. Because each participant invests data and compute, clients need mechanisms to later prove the provenance of a jointly trained model. Model watermarking embeds a hidden signal in the weights, but naive approaches either do not scale with many clients as per-client watermarks dilute as K grows, or give any individual client the ability to verify and potentially remove the watermark. We introduce (t, K)-threshold watermarking: clients collaboratively embed a shared watermark during training, while only coalitions of at least t clients can reconstruct the watermark key and verify a suspect model. We secret-share the watermark key τ so that coalitions of fewer than t clients cannot reconstruct it, and verification can be performed without revealing τ in the clear. We instantiate our protocol in the white-box setting and evaluate it on image classification tasks on both IID and non-IID partitions, as well as language models finetuning setting. Our watermark remains detectable at scale (K = 128) with minimal accuracy loss and stays above the detection threshold (z ≥ 4) under attacks including adaptive fine-tuning using up to 20% of the training data. Code is available at https://github.com/tameemalaa/co llaborative-threshold-watermark.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2602.10765")
get_code_for_paper("2602.10765")
have("2602.10765")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2602.10765.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2602.10765)
Connect an agent — have() is free.