English(EN) The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

新框架统一LLM隐私评估，揭示梯度攻击有效性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-19 04:00

研究人员开发了LLM-Attacker，一个旨在标准化和统一拆分及分布式大型语言模型（LLM）隐私评估的新框架。该框架通过记录攻击者消息、模型权重、数据集和恢复措施相关的选择，实现了隐私评估的可比性和可扩展性。在一项使用GPT-2进行的受控实验中，该框架证明了整合训练梯度可以将令牌恢复率从94.20%显著提高到97.38%，将精确文档恢复率从13.71%提高到37.77%。该系统还区分了实现检查和测量的攻击效果，强调了清晰报告攻击者、数据集和评分规则的必要性。 AI

影响标准化LLM隐私评估，可能导致分布式系统中更强大的数据泄露防御措施。

排序理由该集群包含一篇学术论文，详细介绍了用于评估LLM隐私的新框架。[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: 9 / 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，详细介绍了用于评估LLM隐私的新框架。[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: 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) · Georgios Politis, Evangelos Pappas · 2026-10-19 04:00

LLM-Attacker：用于拆分和分布式LLM系统隐私评估的统一红队框架

arXiv:2610.22722v1 Announce Type: cross Abstract: Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is difficult when attackers see different message…

本文如何被排名

报道来源 [1]

LLM-Attacker：用于拆分和分布式LLM系统隐私评估的统一红队框架

相关实体

相关话题