English(EN) Power Side-Channel Membership Inference Attack on Embedded Machine Learning

新的电源侧信道攻击可从嵌入式设备的电源轨迹推断机器学习训练数据

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

研究人员开发了一种新颖的电源侧信道成员推断攻击（PSCMIA），该攻击可以确定特定数据样本是否用于训练嵌入式机器学习模型。该方法绕过了依赖模型输出（如预测概率或标签）的传统攻击，而是分析模型执行期间的功耗轨迹。PSCMIA 在各种数据集、模型架构（FC 和 CNN）和嵌入式平台上都显示出有效性，实现了高 ROC-AUC 值，并在许多配置中优于仅标签攻击。 AI

影响这项研究突显了嵌入式机器学习系统面临的新隐私风险，可能需要新的防御措施来保护训练数据。

排序理由详细介绍机器学习新安全漏洞的学术论文。[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: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍机器学习新安全漏洞的学术论文。[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) · Sahan Sanjaya, Prabhat Mishra · 2026-10-09 04:00

针对嵌入式机器学习的电源侧信道成员推理攻击

arXiv:2610.10909v1 Announce Type: cross Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a sample was used to train a target model. Existing MIAs rely on model outputs, ranging from prediction probabi…

本文如何被排名

报道来源 [1]

针对嵌入式机器学习的电源侧信道成员推理攻击

相关实体

相关话题