Microsoft 等提出 Detokenization Leaks 攻击,可从 CPU 缓存痕迹重建本地 LLM 输出

DAIR.AI · @dair_ai · X·2026-09-10 02:00·1小时前
AI 导读

Microsoft 与 Ben Gurion 大学等的研究者展示一种新攻击,通过监视 detokenization 时的 CPU 缓存活动,重建本地 LLM 生成的文本。

DAIR.AI@dair_ai
64AI 编辑部评分,满分 100

Microsoft 等提出 Detokenization Leaks 攻击,可从 CPU 缓存痕迹重建本地 LLM 输出

2026-09-10 02:00· 1小时前
AI 导读

Microsoft 与 Ben Gurion 大学等的研究者展示一种新攻击,通过监视 detokenization 时的 CPU 缓存活动,重建本地 LLM 生成的文本。

Wild paper from Microsoft and colleagues.

They show a new attack that reconstructs the text a local LLM generates by watching CPU cache activity while it detokenizes.

Earlier cache attacks needed something unusual in the deployment, such as shared data memory, CPU offloading, or a Mixture-of-Experts architecture. This work targets the detokenizer, which runs in default inference pipelines.

The method has two stages.

  1. Flush+Reload on shared tokenizer code detects when decoding happens, which lets the attacker fire Prime+Probe at the right moment and isolate token-dependent cache activity.
  1. A clustering and language-model pipeline then recovers readable text from the noisy observations.

They evaluate across datasets, hardware platforms, inference frameworks and model families, including real local deployments and agentic systems.

The widely used tokenizer implementations are susceptible, and they are embedded in many popular local LLM products and agent frameworks. OpenClaw is demonstrated directly.

Paper: https://academy.dair.ai/papers/detokenization-leaks-reconstructing-local-llm-outputs-from-cache-traces-2609.06674