Metraipolis › archive › dc_1d759cd78dad

Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks — arXiv:2611.12386

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12386
License (as archived)
CC0-1.0
Archived
2026-11-10T18:44:05.353Z
SHA-256 of the archived text
300b076f2db6d2b2126e0cc66c1d4b3a57fa36ea0932186f91d801573ce685f1
Stable URL of this page
https://metraipolis.com/documento/dc_1d759cd78dad

How to cite

Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks — arXiv:2611.12386 — arXiv (en), https://arxiv.org/abs/2611.12386 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1d759cd78dad (Metraipolis archive dc_1d759cd78dad, sha256 300b076f2db6d2b2126e0cc66c1d4b3a57fa36ea0932186f91d801573ce685f1)
BibTeX
@misc{dc1d759cd78dad,
  title = {Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks — arXiv:2611.12386},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12386},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1d759cd78dad; sha256 300b076f2db6d2b2126e0cc66c1d4b3a57fa36ea0932186f91d801573ce685f1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12386. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study the fingerprinting of agentic cyberattacks. Our objective is to reliably infer information about the attacker's configuration, such as LLM version and harness, from telemetry. To achieve this, we introduce a technique we call shibboleth traps: modular honeypot services designed to elicit discriminative behaviors from agentic attackers. The traps make informative interactions a condition for obtaining resources the agent seeks, eliciting model declarations and characteristic writing without requiring a successful prompt injection. To achieve harness fingerprinting, we introduce general mechanisms to indirectly probe peculiar execution behaviors of harnesses. These probes reveal how a harness masks secrets in tool output, enforces command time limits, and schedules tool calls, using only the effects visible in subsequent requests. We show that combined declarative and behavioral inference distinguishes among 15 candidate models with an average 90% top-1 accuracy, with behavioral classifiers evaluated on held-out harnesses or task families. In a separate experiment across four harnesses, fixed probe rules identify the correct harness with 92% accuracy. When instructed to conceal their identity, agents still leave useful behavioral evidence even as their declarations become uninformative.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.12386 — 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 2026-11-10T18:37:37.691Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).