RESEARCH · RESEARCH · #2978
LanG 2.0: energy-efficient agentic system for large-scale SOC detection (arXiv)
Authors release LanG 2.0 (arXiv:2610.41072v1), an agentic system that uses small local models plus structural safeguards (entity-anchored correlation, human rule-approval, tamper-evident ledger) to detect threats, correlate evidence and write rules for Security Operations Centers. On eight flow datasets, XDR alerts and multistage campaigns, LanG 2.0 raised campaign correlation precision from 18.75% to 51.81% and rule acceptance to 98.33%; it matched or outperformed Claude Opus 5.5 on unseen-network attack detection (73.42% F1 with no false positives vs 58.10% F1 with 49.00% false positives) while using at least ~650x less energy, processed 3.33 million records in 6.4 minutes (~30M+ hourly), and resisted prompt injection, label poisoning and ledger tampering in tests.
KEY POINTS
- Authors release LanG 2.0 (arXiv:2610.41072v1), an agentic system that uses small local models plus structural safeguards (entity-anchored correlation, human rule-approval, tamper-evident ledger) to detect threats, correlate evidence and write rules for Security Operations Centers.
- On eight flow datasets, XDR alerts and multistage campaigns, LanG 2.0 raised campaign correlation precision from 18.75% to 51.81% and rule acceptance to 98.33%; it matched or outperformed Claude Opus 5.5 on unseen-network attack detection (73.42% F1 with no false positives vs 58.10% F1 with 49.00% false positives) while using at least ~650x less energy, processed 3.33 million records in 6.4 minutes (~30M+ hourly), and resisted prompt injection, label poisoning and ledger tampering in tests.
- If validated, LanG 2.0 shows that small local models with structural safeguards can deliver similarly effective, far more energy-efficient and scalable SOC detection and rule generation than frontier models, which matters for operational cost and security governance.
WHY IT MATTERS
If validated, LanG 2.0 shows that small local models with structural safeguards can deliver similarly effective, far more energy-efficient and scalable SOC detection and rule generation than frontier models, which matters for operational cost and security governance.