Skip to content
NewA calmer, faster ZeroHour

ToolPulse recovers LLM agent tool workflows via cache side channels

Original title: ToolPulse: Side-Channel Eavesdropping on Tool-Using LLM Agents

arXiv cs.CRby Zihao Dan ()1 min read3
AI summary · x-ai/grok-4.7Summaries by Vani AI

On 11 models in Codex and Claude Code, tool-workflow F1 stayed above 93%, including under noise on a server shared by about 20 users.

ToolPulse monitors local tool invocations of LLM agents through shared system libraries while model inference stays on vendor infrastructure. Across three hardware platforms, Flush+Reload enabled accurate real-time monitoring, whereas Prime+Probe supported cross-VM observation but had prohibitive overhead and cache-set aliasing. The Tool Recovery Attack reconstructed workflows for 11 LLMs in Codex and Claude Code, with the lowest F1 above 93%. Recovered traces also supported task profiling on two Terminal-Bench categories and localization of sensitive encryption and training calls.

Unconfirmed: Results are from the authors' evaluations, not confirmed attacks on production user systems.

Key facts
  • Flush+Reload outperformed Prime+Probe, which suffered cache-set aliasing.
  • The lowest tool-recovery F1 exceeded 93% across 11 LLMs.
  • Task profiling covered two Terminal-Bench task categories.
  • Trigger localization targeted encryption, decryption, training, and inference calls.
  • Both follow-on attacks kept high accuracy with about 20 users on one server.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at arxiv.org

Large language models (LLMs) are increasingly deployed as agents that translate user requests into sequences of local tool invocations. While prior cache-based side-channel attacks target the locally deployed models, they typically require the adversary to share model-related components or hardware resources with the victim's inference process.

arXiv cs.CR

By Zihao Dan · arxiv.org

Read the full article at arXiv cs.CR

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.