PulseAugur
中
实时 11:58:36
English(EN) One Token Leaked 155 AI Responses: Inside Cloudflare's GLM-5.3 KV Cache Exposure

Cloudflare GLM-5.3 模型因 KV 缓存缺陷泄露客户数据

Cloudflare 发生了一起安全事件,其 Workers AI 上托管的 GLM-5.3 模型存在租户隔离缺陷,导致长度超过 681,280 个 token 的提示词会返回其他客户会话的数据。该问题源于 SGLang 推理引擎中 KV 缓存大小的配置不匹配,未能正确处理超出分配内存的提示词。Cloudflare 在事件声明后数小时内识别并修复了根本原因,并在上游修复部署六周后发布了公开事后复盘。 AI

影响 凸显了托管 LLM 推理中强大的租户隔离机制对于防止数据泄露至关重要。

排序理由 文章详细介绍了托管 AI 模型服务中的一个特定安全漏洞及其解决方案,属于工具和基础设施类别。

在 dev.to — LLM tag 阅读 →

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

Cloudflare GLM-5.3 模型因 KV 缓存缺陷泄露客户数据

本文如何被排名

Signal score
33 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
文章详细介绍了托管 AI 模型服务中的一个特定安全漏洞及其解决方案,属于工具和基础设施类别。
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
product, 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。

报道来源 [1]

  1. dev.to — LLM tag TIER_1 English(EN) · Damiano ·

    一个 Token 泄露 155 个 AI 回应:揭秘 Cloudflare 的 GLM-5.3 KV 缓存暴露事件

    <p>On September 8, 2026, a security researcher told Cloudflare that very long prompts sent to one of its hosted models sometimes came back with text from other customers' sessions. Cloudflare reproduced the leak within a day, took the model offline forty minutes after declaring a…