Metraipolis › archive › dc_84ce3e0cd680

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces — arXiv:2610.41885

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41885
License (as archived)
CC0-1.0
Archived
2026-11-03T07:55:27.961Z
SHA-256 of the archived text
b05193ecbfcc58687d9626de4ba1172aab0f08b064169b38a87364b2782e3cb5
Stable URL of this page
https://metraipolis.com/documento/dc_84ce3e0cd680

How to cite

How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces — arXiv:2610.41885 — arXiv (en), https://arxiv.org/abs/2610.41885 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84ce3e0cd680 (Metraipolis archive dc_84ce3e0cd680, sha256 b05193ecbfcc58687d9626de4ba1172aab0f08b064169b38a87364b2782e3cb5)
BibTeX
@misc{dc84ce3e0cd680,
  title = {How Much Can Tool Calls Reveal About You? Privacy Leakage from Tool-Call Traces — arXiv:2610.41885},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41885},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84ce3e0cd680; sha256 b05193ecbfcc58687d9626de4ba1172aab0f08b064169b38a87364b2782e3cb5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41885. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.41885 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T07:49:46.035Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).