English(EN) Is the Hard-Label Cryptanalytic Model Extraction Really Polynomial?

新研究质疑深度神经网络模型提取的多项式时间复杂度

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-26 04:00

一篇新的研究论文对从深度神经网络（DNN）提取信息总是多项式时间过程的假设提出了质疑。尽管之前的工作表明硬标签提取攻击（仅揭示最终分类）是高效的，但该论文认为复杂性随着网络深度的增加而增加。作者提出了一种新颖的跨层提取方法来克服这些限制。 AI

影响对模型提取攻击的效率假设提出挑战，可能影响深度神经网络的知识产权保护。

排序理由在arXiv上发表的学术论文，讨论了深度神经网络模型提取攻击的理论局限性。[lever_c_demoted from research: ic=1 ai=1.0]

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; 在arXiv上发表的学术论文，讨论了深度神经网络模型提取攻击的理论局限性。[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: 55 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。

arXiv cs.LG TIER_1 English(EN) · Akira Ito, Takayuki Miura, Yosuke Todo · 2026-08-26 04:00

硬标签密码分析模型提取真的多项式时间复杂度吗？

arXiv:2510.06692v3 Announce Type: replace Abstract: Deep Neural Networks (DNNs) have attracted significant attention, and their internal models are now considered valuable intellectual assets. Extracting such a model via oracle access to a DNN is conceptually similar to extractin…