PulseAugur
中
实时 17:39:16
English(EN) A Constant-Time Implementation Methodology for Activation Functions on Microcontrollers

新方法保护嵌入式神经网络免受计时攻击

研究人员开发了一种新的嵌入式神经网络激活函数实现方法,可防止通过计时侧信道泄露信息。该方法通过采用无分支选择和固定成本近似等技术,确保所有输入的执行时间一致,而与所使用的具体激活函数无关。在带有常见激活函数的 ARM Cortex-M4 平台上进行测试,受保护的实现获得了相同的周期计数,同时保持了高数值精度,为安全的嵌入式推理提供了一个实用的解决方案。 AI

影响 通过减轻基于时间的侧信道攻击来增强嵌入式人工智能系统的安全性。

排序理由 该集群包含一篇学术论文,详细介绍了在微控制器上实现激活函数的新方法。[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 →

新方法保护嵌入式神经网络免受计时攻击

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
该集群包含一篇学术论文,详细介绍了在微控制器上实现激活函数的新方法。[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, infra
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
140 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]

  1. arXiv cs.AI TIER_1 English(EN) · Xiaolu Hou ·

    面向微控制器的激活函数常数时间实现方法论

    Embedded neural-network inference can leak information through timing side channels, including leakage caused by the evaluation of activation functions. This work proposes a constant-time implementation methodology for activation functions on embedded microcontrollers and validat…