Metraipolis › archive › dc_4d53a526d043
APEX: Active Protection at Execution Boundaries for LLM Agents — arXiv:2610.06966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.06966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:04.570Z
- SHA-256 of the archived text
0972b76a60200d64e2b9e1e9a0e3048946fdf73c428bb745fac93b3df9197a3a- Stable URL of this page
https://metraipolis.com/documento/dc_4d53a526d043
How to cite
APEX: Active Protection at Execution Boundaries for LLM Agents — arXiv:2610.06966 — arXiv (en), https://arxiv.org/abs/2610.06966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d53a526d043 (Metraipolis archive dc_4d53a526d043, sha256 0972b76a60200d64e2b9e1e9a0e3048946fdf73c428bb745fac93b3df9197a3a)
BibTeX
@misc{dc4d53a526d043,
title = {APEX: Active Protection at Execution Boundaries for LLM Agents — arXiv:2610.06966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.06966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d53a526d043; sha256 0972b76a60200d64e2b9e1e9a0e3048946fdf73c428bb745fac93b3df9197a3a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind them. We instead shift defense from covering attack patterns to one stable point: whatever the carrier and however the injection propagates, harm materializes only at the \emph{execution boundary}, where the agent turns internal state into an external action or released output. Safety there turns on two conditions, both settled by the trusted task rather than by the run: whether the proposed effect is authorized, and whether the runtime information reaching it is endorsed by that task. We present APEX, an active defense that enforces both at this boundary from a single authorization contract compiled before untrusted execution: \emph{evidence-gated prevention} admits an effect only when the contract justifies it, while \emph{deception-based exposure} makes unendorsed use reveal itself before the effect commits. Protection therefore follows from what the task permits rather than from how an attack is built, and applies uniformly across capability units without attack-specific policies or taint tracking. Against 13 baselines, APEX attains 0\% attack success on five of six benchmarks and 0.56\% on the sixth, holds 0\% under adaptive attacks on all three capability-unit types, and remains effective across defender backbones. Code is available at this https URL .
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/2610.06966 — 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 2026-10-07T11:15:24.650Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).