Metraipolis › archive › dc_a098ace65538

Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks — arXiv:2609.12839

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12839
License (as archived)
CC0-1.0
Archived
2026-10-16T03:03:38.034Z
SHA-256 of the archived text
a95270e029b6da6ded0cf210e551d60c91ad2dbe678ffd3d0ccaf806b265e64d
Stable URL of this page
https://metraipolis.com/documento/dc_a098ace65538

How to cite

Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks — arXiv:2609.12839 — arXiv (en), https://arxiv.org/abs/2609.12839 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a098ace65538 (Metraipolis archive dc_a098ace65538, sha256 a95270e029b6da6ded0cf210e551d60c91ad2dbe678ffd3d0ccaf806b265e64d)
BibTeX
@misc{dca098ace65538,
  title = {Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks — arXiv:2609.12839},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12839},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a098ace65538; sha256 a95270e029b6da6ded0cf210e551d60c91ad2dbe678ffd3d0ccaf806b265e64d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12839. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing an escalating risk as these models can bypass proprietary API guardrails when deployed locally. However, SLMs deployed as autonomous agents often struggle with long-horizon, exploratory tasks like cybersecurity Capture The Flag (CTF) challenges due to context bloat and cognitive degradation from accumulated tool-call outputs. To understand and mitigate this cybersecurity threat, we introduce context segmentation, a two-level agentic framework that divides complex exploitation tasks into manageable, contextually isolated sub-problems. Evaluating on the picoCTF dataset using memory-constrained gemma-4 models, we demonstrate that for the E4B model, our strategy acts as an intelligent search, achieving competitive rewards with superior token efficiency compared to brute-force retries, and successfully solving 18.52% of tasks that standard agentic execution fails to complete. Code is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.12839 — 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 2026-10-16T02:51:27.945Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).