arXiv Machine Learning
GenoTrace: Inheritable Watermarks for Genome Foundation Model Distillation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jun 18
Signature filtering: a lightweight enhancement for statistical watermark detection in large language models
arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.
arXiv Machine Learning
2d ago
Steal the Knowledge, Inherit the Mark: TwinMark for Distillation Watermarking via Second Moments and Class Multiplexing
arXiv:2609.19011v2 Announce Type: replace Abstract: Knowledge distillation can copy a deployed model by training a student on its logits or features. The student inherits a watermark only through the...
Hugging Face Trending Papers
Sep 3
Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference
We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials. Unlike KGW's vocabulary permutation or SynthID's multi-layer tournament, SBW requires only a single comparison per token against a counter-based random number generator, reducing membership complexity to $O(1)$ and enabling single-kernel execution with zero intermediate allocations.
arXiv Machine Learning
4d ago
BarcodeMAE+: Rethinking Masked Pretraining and Global Representations for DNA Barcode Foundation Models
arXiv:2609.35877v1 Announce Type: cross Abstract: Many DNA foundation models are pretrained by masking parts of a sequence and asking the model to reconstruct them. Standard masked pretraining expose...
arXiv Machine Learning
Sep 4
Flip, Don't Shuffle: Watermarking LLMs at the Speed of Inference
arXiv:2609. 03844v1 Announce Type: cross Abstract: We introduce Stateless Bernoulli Watermarking (SBW), a new statistical watermark for Large Language Models that determines green list membership through independent per-token Bernoulli trials.
arXiv Computer Vision
6d ago
FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models
FeatMark is a watermarking framework that protects images from text‑to‑image diffusion model mimicry attacks by embedding small, scene‑consistent micro‑features instead of pixel‑level perturbations. It constructs domain‑specific feature banks, selects executable features, and injects them via mask‑guided concept editing to create highly localized, natural edits. Experiments on VGGFace2, CelebA‑HQ, and WikiArt show FeatMark remains robust against ten strong watermark removal attacks and several adaptive attacks, with minimal impact on perceptual quality and extending to video mimicry scenarios.