paperSeptember 2026Unreviewed

Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks

Sebastiano Nordio, Michele Lotto

Abstract

The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing a 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 th

Cite

@misc{nordio2026evaluating,
  title = {{Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks}},
  author = {Sebastiano Nordio and Michele Lotto},
  year = {2026},
  month = sep,
  eprint = {2609.12839},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.12839}
}