analiza aiqbench
The paper argues that small local models, paired with structural safeguards like human-approved rule changes and a tamper-evident ledger, can handle most SOC detection tasks at a fraction of the energy of frontier models. Its headline comparisons, including the 650x energy gap against Claude Opus 5.5 and the 73.42% F1 on unseen networks, are self-reported on a preprint, so reproducibility and the datasets' representativeness matter. For AI readers, the main point is the design claim that guarantees can come from system architecture rather than model accuracy.
LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale
arXiv:2610.41072v1 Announce Type: new Abstract: 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.
Title:LanG 2.0: Energy-Efficient Agentic AI for Semi-Automated Security Operations at Scale
Abstract: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.
Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR)
arXiv:2610.41072 [cs.AI]
(or arXiv:2610.41072v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.41072 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 306 cuvinte