English(EN) Characterizing Contention-Induced Reliability Collapse in KV-Cache Timing Side Channels for Multi-Tenant LLM Serving

KV缓存侧信道在LLM服务负载下可靠性崩溃

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

研究人员调查了多租户LLM服务环境中KV缓存时序侧信道的可靠性。他们的实验表明，来自多个用户的争用会显著降低这些侧信道的可靠性，可能高估其在安静系统上的运行攻击可行性。研究发现，并发深度和服务堆栈严重影响此类攻击的有效性。 AI

影响理解KV缓存侧信道漏洞对于保护多租户LLM部署和确保数据隐私至关重要。

排序理由这是一篇详细介绍LLM服务安全研究结果的研究论文。[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: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇详细介绍LLM服务安全研究结果的研究论文。[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。

arXiv cs.AI TIER_1 English(EN) · Rana Abu Bakar · 2026-09-10 04:00

面向多租户LLM服务的缓存 KV 定时侧信道中争用诱导的可靠性崩溃特征分析

arXiv:2609.06853v1 Announce Type: cross Abstract: Shared key--value (KV) cache reuse improves large language model (LLM) serving, but it can also create a timing side channel that reveals whether a prefix is already cached. Previous work shows that such attacks are possible, but …