SEAL: Entangled White-box Watermarks on Low-Rank Adaptation

Giyeong Oh, SJKIM, CHO WOOHYUN, Sangkyu Lee, Jiwan Chung, Dokyung Song, Youngjae Yu

SEAL: Entangled White-box Watermarks on Low-Rank Adaptation: 8 upvotes on Hugging Face Daily Papers, #3 of 3 papers on 2025-01-21. Day-by-day upvote history.

Recently, LoRA and its variants have become the de facto strategy for training and sharing task-specific versions of large pretrained models, thanks to their efficiency and simplicity. However, the issue of copyright protection for LoRA weights, especially through watermark-based techniques, remains underexplored. To address this gap, we propose SEAL (SEcure wAtermarking on LoRA weights), the universal whitebox watermarking for LoRA. SEAL embeds a secret, non-trainable matrix between trainable LoRA weights, serving as a passport to claim ownership. SEAL then entangles the passport with the LoRA weights through training, without extra loss for entanglement, and distributes the finetuned weights after hiding the passport. When applying SEAL, we observed no performance degradation across commonsense reasoning, textual/visual instruction tuning, and text-to-image synthesis tasks. We demonstrate that SEAL is robust against a variety of known attacks: removal, obfuscation, and ambiguity attacks.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.