AI PAPERS/DAILY
Subscribe free Open sourceView on GitHub Star This project is open sourceRead the code or use it in your own project. If you like it, don’t forget to give it a ★ star on GitHub.

All papersLLMs & Language ModelsShanghai AI Lab

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces

/ Paper arXiv 2610.41885

Key numbers

26.25%…mainstream LLM attackers show that tool-call traces enable a 26.25% attack success rate for profile inference
17.97%compared with 17.97% from prior-based guessing
4,000a benchmark containing 1,000 synthetic user profiles and 4,000 agent trajectories across four domains

From the paperCopied from the abstract, not written by AI.

Abstract

From the paperThe authors' own words.

Large language model (LLM)-based agents interact with external tools through protocols such as the Model Context Protocol (MCP), producing tool-call traces that may expose behavioral signals about users. In this work, we systematically study the risk of user-profile inference from MCP tool-call traces, where observers infer user attributes from protocol-valid tool interactions without access to user conversations. We introduce PrivacyTrace, a benchmark containing 1,000 synthetic user profiles and 4,000 agent trajectories across four domains, generated with real MCP tools from 25 servers. Experiments with four mainstream LLM attackers show that tool-call traces enable a 26.25% attack success rate for profile inference, compared with 17.97% from prior-based guessing. Further analysis reveals that tool arguments and returned results provide the main trace-grounded evidence, while linking traces across sessions further amplifies profiling risk. These findings demonstrate that MCP tool-call traces can act as effective behavioral side channels for user profiling, motivating the development of privacy-aware mechanisms for agent-tool interactions. Code and data are available at https://github.com/AI45Lab/PrivacyTrace.

From the full paper

From the paperCopied from the paper itself by our code.

Reading the paper on arXiv…

Try it

Code, models and demos that use this paper.

Ask this paper

/ Ask a questionAnswers come from the full paper and name the section

    / Your notes

    Select text in the abstract to highlight it or add a note. They stay in this browser.

      / Read next, same idea

      Read the PDF