PulseAugur
中
实时 22:45:07
English(EN) Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy

新方法增强局部差分隐私对抗投毒攻击

研究人员开发了一种名为随机投影裁剪(RPC)的新方法,用于防御局部差分隐私(LDP)协议中的投毒攻击。该方法适用于拥有多个数据项的用户,在这种情况下,由于输出空间更大,现有防御措施的效果会减弱,从而使对手更有能力。RPC 包括用户将本地数据投影到服务器发送的随机向量上,然后对结果进行裁剪以限制攻击能力。研究人员还引入了一种校正方法来解决裁剪偏差问题,从而在不影响偏差-方差权衡的情况下降低裁剪阈值并提高鲁棒性。理论保证和数值实验证明了 RPC 在可信和不可信环境中的有效性,其性能与现有方法相当或更优,并且在对抗投毒方面具有显著的鲁棒性提升。 AI

影响 增强分布式机器学习系统的隐私保证。

排序理由 学术论文,详细介绍了一种新的隐私协议方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新方法增强局部差分隐私对抗投毒攻击

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
学术论文,详细介绍了一种新的隐私协议方法。[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
89 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 stat.ML TIER_1 English(EN) · Puning Zhao, Zhikun Zhang, Shaowei Wang, Sheng Yue, Bangzhou Xin, Tianhang Zheng, Pengfei Zhang, Xiaochun Cao ·

    局部差分隐私下稀疏数值向量的鲁棒估计

    arXiv:2607.27815v1 Announce Type: new Abstract: Local differential privacy (LDP) protocols are vulnerable to poisoning attacks. Existing research have proposed efficient defense strategies for single-item users. However, in practice, a user may possess multiple items. The defense…