MeMark introduces a watermarking scheme for Spiking Neural Networks that embeds a multi‑bit identifier directly into the membrane state of selected Leaky Integrate‑and‑Fire neurons, rather than in the output head. The watermark is recoverable by comparing neuron firing thresholds, eliminating the need for a learned decoder. Experiments on various SNN architectures—including a 215.4M‑parameter SpikeGPT checkpoint—show that all 20 independent 64‑bit keys reliably pass verification under a 51/64 rule, remain robust after fine‑tuning, pruning, quantization, and output‑head replacement, and are not recovered by random keys or adaptive attacks within the tested threat model.
By Roberto Ria\~no, Gorka Abad, Stjepan Picek, Aitor Urbieta
arXiv:2409. 06130v2 Announce Type: replace-cross Abstract: Modern machine learning models require substantial computational resources and data to train, making them valuable intellectual property.
By Aoting Hu, Yanzhi Chen, Renjie Xie, Xinwei Zhang, Wei Xu
arXiv:2606. 11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures.
By Jian-Ping Mei, Weibin Zhang, Ao Yao, Tiantian Zhu, Jie Xiao
The paper introduces CertDW, a certified dataset watermark and ownership verification method that remains reliable even under malicious perturbations. By leveraging conformal prediction, it defines two statistical measures—principal probability (PP) and watermark robustness (WR)—to evaluate model stability on benign versus watermarked samples. The authors derive certification conditions linking WR to a PP-based threshold and provide a high‑probability bound on false positives, enabling robust ownership verification when a suspicious model’s WR exceeds the PP values of benign models.
By Ting Qiao, Yiming Li, Jianbin Li, Yingjia Wang, Leyi Qi, Junfeng Guo, Ruili Feng, Dacheng Tao
arXiv:2609.32241v2 Announce Type: replace-cross
Abstract: Neural image watermarks can be forged by extracting watermark-bearing residuals from released images and transferring them to unrelated conte...
By Ziping Dong, Qi Li, Xinchao Wang
arXiv:2607. 13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for reliable watermarking techniques.
By Z Sun, Q Jiang, S Sheng, L Xiang
arXiv:2610.15725v2 Announce Type: cross
Abstract: Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to una...
By Alan Tang, Lifeng Wang, Gang Wu, Tao Zhang, Yantao Jia, Xiaofeng Zhu
arXiv:2607. 20435v1 Announce Type: cross Abstract: Open-source LLMs (OSMs)arereaching near state-of-the-art performance, prompting prior works to trace the text they generate by embedding text watermarking algorithms directly into their weights.
By Luisa Scharff, Thibaud Gloaguen, Robin Staab, Martin Vechev
MarkTune is a model‑embedded watermarking framework that improves the trade‑off between generation quality and detectability. By regularizing toward a high‑quality reference distribution, it decouples quality preservation from proximity to the base model and uses the GaussMark detection statistic as a reward during on‑policy fine‑tuning. Empirical results show that MarkTune enhances the quality‑detectability frontier, maintains downstream task performance, and remains robust against text‑editing and open‑weight attacks across diverse datasets.
By Yizhou Zhao, Zhiwei Steven Wu, Adam Block
The paper introduces REMARK, a watermark‑based fingerprint framework designed to verify ownership of Graph Neural Networks (GNNs). REMARK generates in‑distribution watermark graphs that maximize output differences between GNN models, thereby reducing performance loss from out‑of‑distribution watermarks. It then extracts robust fingerprints from these output differences, eliminating the need for surrogate models trained on watermark data or reliance on specific output levels, and achieves state‑of‑the‑art verification accuracy across real‑world datasets and GNN architectures.
By Han Zhang, Yan Wang, Guanfeng Liu, Pengfei Ding, Huaxiong Wang, Kwok-Yan Lam
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.
By Haoyang Li, Ruoxi Sun, Qingqing Ye, Benjamin Zi Hao Zhao, Yaxin Xiao, Jason Xue, Haibo Hu
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.
By Chih-Duo Hong, Yen-Pang Chen, Fang Yu