GenoTrace：面向基因组基础模型蒸馏的可继承水印

This paper has been withdrawn by Guang Yang

No PDF available, click to view other formats

Abstract:Can a genome model retain a detectable record of the synthetic sequences used to train it? We study watermark inheritance through distillation with GenoTrace, a codon-aware extension of green-list watermarking. Two token-level factors modulate the teacher's generation bias using codon position and organism-specific codon usage. The resulting sequences train a smaller student, whose outputs are audited without an active watermark processor. In a three-seed GenomeOcean-500M-to-100M experiment, the joint configuration achieves a mean audit score of 17.88 and 94.5% detection at a fixed threshold. It retains 49.0% detection after key-aware token substitution, compared with 0% for the available single-seed plain-watermark comparator, and 47.0% after combined mechanism-targeted nucleotide edits. Additional experiments establish inherited signal across five organism-conditioned datasets and teacher-student size ratios up to 40. Component ablations and computational sequence-quality assays reveal distinct operating points for detection strength and coding coverage. GenoTrace provides a practical token-level construction and an empirical account of how genomic structure shapes inherited watermark signals. The findings concern shared-tokenizer distillation and the tested editing procedures, with calibration and biological utility treated as separate evaluation requirements.

Comments:	Withdrawn by the authors pending an institutional intellectual property review
Subjects:	Cryptography and Security (cs.CR); Machine Learning (cs.LG); Genomics (q-bio.GN)
Cite as:	arXiv:2609.35881 [cs.CR]
	(or arXiv:2609.35881v2 [cs.CR] for this version)
	https://doi.org/10.48550/arXiv.2609.35881 arXiv-issued DOI via DataCite

Submission history

From: Guang Yang [view email]
[v1] Sun, 27 Sep 2026 00:15:38 UTC (1,512 KB)
[v2] Thu, 1 Oct 2026 22:13:43 UTC (1 KB) (withdrawn)