Metraipolis › archive › dc_4bb29c19fea5

LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale — arXiv:2610.41072

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41072
License (as archived): CC0-1.0
Archived: 2026-11-03T08:00:40.326Z
SHA-256 of the archived text: 60bb21cf29aae70491221366330336033e7880c2e12be19ddc2c7b555429437f
Stable URL of this page: https://metraipolis.com/documento/dc_4bb29c19fea5

How to cite

LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale — arXiv:2610.41072 — arXiv (en), https://arxiv.org/abs/2610.41072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bb29c19fea5 (Metraipolis archive dc_4bb29c19fea5, sha256 60bb21cf29aae70491221366330336033e7880c2e12be19ddc2c7b555429437f)

BibTeX

@misc{dc4bb29c19fea5,
  title = {LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale — arXiv:2610.41072},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41072},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bb29c19fea5; sha256 60bb21cf29aae70491221366330336033e7880c2e12be19ddc2c7b555429437f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41072. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Security operations centers (SOCs) need to turn terabytes of alerts, logs and flows into trusted, affordable decisions to unveil hidden threats. We present LanG 2.0, an agentic system that detects threats, correlates evidence and writes rules, investigating whether small local models can replace frontier models affordably and safely when structural safeguards, not model accuracy, provide the guarantees. It incorporates entity-anchored correlation, human approval of rule changes and a tamper-evident ledger. Tests span eight flow datasets from five networks, real XDR alerts and multistage campaigns. Against its predecessor, campaign correlation precision rises from 18.75% to 51.81%, and rule acceptance from at most 60.00% to 98.33%. Against Claude Opus 5.5, scoring flows against each network's normal traffic detects attacks on unseen networks at 73.42% F1 without false positives, versus 58.10% with 49.00% false positives, for at least 650 times less energy. Finetuned models statistically match it on alert classification and rule writing for 5.6 to 59 times less energy. The work demonstrates LanG's practical scalability, processing 3.33 million records in 6.4 minutes, over 30 million hourly, and its safeguards resisted prompt injection, label poisoning and ledger tampering, so small local models can carry most SOC detection affordably and safely.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.41072 — 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 2026-11-03T07:59:38.682Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).