English(EN) No Escape from the Quadratic Barrier: Adaptive Attacks on Linear $\ell_2$ Sketches

对线性草图的自适应攻击触及二次方障碍

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员已经证明，对线性草图（用于压缩高维数据）的自适应攻击在根本上受到二次方障碍的限制。即使响应者了解所有攻击细节并能调整其策略，最优隐私保证也是 $\widetilde{\Omega}(k^2)$，其中 $k$ 是草图维度。该研究表明，对于任何隐藏矩阵 $A$ 和精度 $\alpha$，自适应黑盒攻击都可以迫使相当一部分答案具有实质性的相对误差，从而阐明了线性表示防御的局限性。 AI

排序理由学术论文，详细介绍数据压缩和隐私方面的理论计算机科学研究。[lever_c_demoted from research: ic=1 ai=0.4]

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: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍数据压缩和隐私方面的理论计算机科学研究。[lever_c_demoted from research: ic=1 ai=0.4]
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, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: Standard; On-topic for AI-industry coverage; kept in the public index.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Edith Cohen, Uri Stemmer · 2026-11-06 05:00

无法逃脱二次方障碍：对线性 $\ell_2$ 草图的自适应攻击

arXiv:2610.25008v2 Announce Type: replace-cross Abstract: Linear sketches estimate properties of high-dimensional inputs from a fixed low-dimensional projection. At constant accuracy, randomized Euclidean-norm sketches, notably the Johnson-Lindenstrauss transform, support exponen…

本文如何被排名

报道来源 [1]

无法逃脱二次方障碍：对线性 $\ell_2$ 草图的自适应攻击

相关实体

相关话题