Metraipolis › archive › dc_50bc49f7300a

SecJev: Bringing Security Expertise to System One Decision Models — arXiv:2610.03073

Source: arXiv
Original: https://arxiv.org/abs/2610.03073
License (as archived): CC0-1.0
Archived: 2026-10-05T22:51:59.304Z
SHA-256 of the archived text: 699ab951d65c4ef7046d2b89a73e356c9cca54fca40e978314eee5df6dbd17ea
Stable URL of this page: https://metraipolis.com/documento/dc_50bc49f7300a

How to cite

SecJev: Bringing Security Expertise to System One Decision Models — arXiv:2610.03073 — arXiv, https://arxiv.org/abs/2610.03073 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_50bc49f7300a (Metraipolis archive dc_50bc49f7300a, sha256 699ab951d65c4ef7046d2b89a73e356c9cca54fca40e978314eee5df6dbd17ea)

BibTeX

@misc{dc50bc49f7300a,
  title = {SecJev: Bringing Security Expertise to System One Decision Models — arXiv:2610.03073},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.03073},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_50bc49f7300a; sha256 699ab951d65c4ef7046d2b89a73e356c9cca54fca40e978314eee5df6dbd17ea},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.03073. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed predictions and probabilities; security specialization supplies the domain expertise behind those predictions. We introduce SecJev, to our knowledge the first family of Jev-like decision models specialized for security, spanning 0.8B to 9B parameters. Built on Kev's single-pass candidate scorer, SecJev learns Boolean, choice, and ordered decisions from text, telemetry, and observation histories. We develop SecJev-Corpus to unify source-label prediction and explicit-policy evaluation across 14 tasks and eight sources. It covers tool outputs, traffic, federated updates, consensus, authentication, and vehicle messages. Scene-weighted training adapts the models across these domains while preserving a shared typed decision interface. Security specialization improves every model in the family; SecJev-0.8B outperforms general Kev-9B by 20.51 percentage points in task-macro accuracy. Comparisons with answer-only generative fine-tuning show close accuracy and latency with lower peak inference memory. Tests on new source groups reproduce gains over Kev in prompt-injection and traffic decisions, with capture-dependent false alarms. We release adapters, decision heads, SecJev-Corpus, and training and inference code.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.03073 — 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 2026-10-05T22:46:10.622Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).