English(EN) Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples

新的MDSE攻击欺骗脉冲神经网络和传统模型

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-22 04:00

研究人员开发了一种名为混合动态脉冲估计（MDSE）的新型对抗攻击方法，专门用于脉冲神经网络（SNN）。该攻击表明，白盒对抗攻击对SNN的有效性在很大程度上受到代理梯度估计器选择的影响。MDSE攻击旨在同时利用多个代理梯度估计器，使其能够生成欺骗SNN和传统非SNN模型（如Vision Transformers和CNNs）的对抗样本。 AI

影响引入了一种可以欺骗SNN和传统神经网络的新型攻击，突显了节能AI模型的安全漏洞。

排序理由学术论文，详细介绍了SNN的新型对抗攻击方法。[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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了SNN的新型对抗攻击方法。[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: 139 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Nuo Xu, Kaleel Mahmood, Haowen Fang, Ethan Rathbun, Caiwen Ding, Wujie Wen · 2026-05-22 04:00

攻击Spike：关于Spiking Neural Networks对对抗性样本的可迁移性和安全性

arXiv:2209.03358v5 Announce Type: replace-cross Abstract: Spiking neural networks (SNNs) have attracted much attention for their high energy efficiency and recent advances in classification performance. However, unlike traditional deep learning approaches, the study of SNN robust…

本文如何被排名

报道来源 [1]

攻击Spike：关于Spiking Neural Networks对对抗性样本的可迁移性和安全性

相关实体

相关话题