English(EN) MeMark: Membrane-Space Watermarking for Spiking Neural Networks

新的MeMark技术将水印嵌入SNN神经元状态

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-27 04:00

研究人员开发了一种名为MeMark的新型脉冲神经网络（SNN）水印技术，以防止未经授权的预训练模型重用。与之前侧重于输出验证的方法不同，MeMark将多比特标识符嵌入选定的泄漏积分发放（LIF）神经元的内部膜状态。这种方法无需学习解码器即可进行验证，并在大型SpikeGPT检查点上进行了测试，证明了其对微调、剪枝、量化和输出头替换等各种攻击的鲁棒性。 AI

影响这种水印方法可以加强人工智能模型的知识产权保护，特别是在不断发展的脉冲神经网络领域。

排序理由该集群包含一篇详细介绍AI模型水印新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 23 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI模型水印新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Roberto Ria\~no, Gorka Abad, Stjepan Picek, Aitor Urbieta · 2026-08-27 04:00

MeMark：脉冲神经网络的膜空间水印

arXiv:2608.25738v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) are increasingly distributed as pretrained checkpoints and reused as backbones for new tasks. However, current SNN watermarks are mainly verified against the model output. Thus, a user who replaces t…

本文如何被排名

报道来源 [1]

MeMark：脉冲神经网络的膜空间水印

相关实体

相关话题