arXiv cs.AI· Yuyang Zhang, Kangjie Chen, Yihui Jin, Run Wang·· 12 小时前AI 评分31
一个设备上的模型暴露会危及他人：重新审视跨设备边缘神经网络安全
Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across Devices
AI 导读
研究提出 VeilNN 防御框架，通过模型混淆降低端侧模型间的对抗样本可迁移性，从而抵御跨节点攻击。VeilNN 在网络结构和参数两个层面施加隐蔽且不可逆的混淆，适用于 MLP、CNN 和 Vision Transformer。实验显示其对四类对抗攻击的平均防御成功率为 49.19%，最高达 81.19%，比现有防御提升超过 33.16%。
正文 · 原文
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 applications can be unpacked and exposed to adversaries, enabling cross-node attacks in centrally distributed ecosystems, where adversarial examples crafted on one compromised device transfer effectively to other nodes sharing the same models. To address this threat, we propose VeilNN, a defense framework that reduces adversarial transferability across on-device models via model obfuscation. The core idea of VeilNN is to introduce controlled model diversity while preserving original task functionality. Specifically, VeilNN applies stealthy and irreversible obfuscation at both the architectural and parameter levels through network cell obfuscation and layer assembling, and is applicable to diverse NN architectures, including MLPs, CNNs, and Vision Transformers. Extensive experiments demonstrate that VeilNN effectively defends against cross-node attacks, achieving an average defense success of 49.19% and up to 81.19% across four adversarial attack types, with more than 33.16% improvement over existing defenses.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.27152 [cs.CR] |
| (or arXiv:2610.27152v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.27152 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yihui Jin [view email]
[v1]
Mon, 19 Oct 2026 18:45:18 UTC (424 KB)
来源：arXiv cs.AI · arxiv.org