Metraipolis › archive › dc_08810c0f4e2e

StateFence: Task-State Protection Against Evidence-Chain Contamination in Blue-Team LLM Agents — arXiv:2611.02605

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02605
License (as archived)
CC0-1.0
Archived
2026-11-03T18:20:00.088Z
SHA-256 of the archived text
9b2d29a64f679532daa9c6c38c019173c128a6a26f4dee74dc430c3623b78b77
Stable URL of this page
https://metraipolis.com/documento/dc_08810c0f4e2e

How to cite

StateFence: Task-State Protection Against Evidence-Chain Contamination in Blue-Team LLM Agents — arXiv:2611.02605 — arXiv (en), https://arxiv.org/abs/2611.02605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08810c0f4e2e (Metraipolis archive dc_08810c0f4e2e, sha256 9b2d29a64f679532daa9c6c38c019173c128a6a26f4dee74dc430c3623b78b77)
BibTeX
@misc{dc08810c0f4e2e,
  title = {StateFence: Task-State Protection Against Evidence-Chain Contamination in Blue-Team LLM Agents — arXiv:2611.02605},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02605},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08810c0f4e2e; sha256 9b2d29a64f679532daa9c6c38c019173c128a6a26f4dee74dc430c3623b78b77},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Indirect prompt injection creates a distinctive risk for blue-team Large Language Model (LLM) agents in Security Operations Centers (SOCs). Malicious instructions can be embedded in telemetry, tickets, retrieval results, or memory and then propagate through alert triage, incident summarization, response recommendation, and Indicator of Compromise (IOC) extraction as locally plausible intermediate decisions. We characterize this failure mode as evidence-chain contamination of protected task state. The main challenge is task dependent: a suspicious string may be malicious control text for summarization but essential evidence for IOC extraction. To address this challenge, we propose StateFence, a task-aware evaluation and defense framework that treats severity labels, incident narratives, response policies, and IOC sets as protected states. StateFence maps indirect prompt-injection attacks into explicit, stealth, multi-hop, and persistent SOC evidence attacks, records observable propagation traces, and routes defenses according to the attacked state. Across controlled SOC cases and public-SOC validation cases, StateFence lowers attack success and reduces failures that appear only after evidence is poisoned, while preserving task utility and avoiding the indicator loss caused by task-mismatched filtering. Our findings indicate that robust blue-team LLM agents require mechanisms that preserve task-critical state under untrusted evidence.

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/2611.02605 — 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 2026-11-03T18:09:53.694Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).