English(EN) Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices

VeilNN框架增强边缘神经网络安全性，抵御对抗性攻击

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员开发了VeilNN，一个旨在保护部署在边缘设备上的神经网络免受跨节点对抗性攻击的新型防御框架。该框架通过架构和参数混淆引入受控的多样性，使得攻击者难以将在一个受损设备上精心设计的攻击转移到共享相同模型的其他设备上。VeilNN已显示出显著的有效性，在各种攻击类型和神经网络架构上，与现有方法相比，防御成功率提高了33.16%以上。 AI

影响增强了部署在边缘设备上的AI模型的安全性，可能促进在隐私敏感应用中更广泛地采用设备端AI。

排序理由详细介绍边缘神经网络新安全框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍边缘神经网络新安全框架的研究论文。[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: 2 days old; Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yuyang Zhang, Kangjie Chen, Yihui Jin, Run Wang · 2026-10-21 04:00

单一设备上的模型暴露危及其他设备：跨设备边缘神经网络安全再思考

arXiv:2610.27152v1 Announce Type: cross Abstract: Neural networks (NNs) are increasingly deployed on edge devices such as mobile and IoT platforms, offering low latency and improved privacy compared to cloud-based deployment. However, on-device models embedded in mobile applicati…

本文如何被排名

报道来源 [1]

单一设备上的模型暴露危及其他设备：跨设备边缘神经网络安全再思考

相关实体

相关话题