mlsanityData to 14 Oct 2026

LanG -- A Governance-Aware Agentic AI Platform for Unified Security Operations

arXiv 2604.05440 ↗First posted 7 Apr 2026cs.CR cs.AIcited by 1

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

Modern Security Operations Centers struggle with alert fatigue, fragmented tooling, and limited cross-source event correlation. Challenges that current Security Information Event Management and Extended Detection and Response systems only partially address through fragmented tools. This paper presents the LLM-assisted network Governance (LanG), an open-source, governance-aware agentic AI platform for unified security operations contributing: (i) a Unified Incident Context Record with a correlation engine (F1 = 87%), (ii) an Agentic AI Orchestrator on LangGraph with human-in-the-loop checkpoints, (iii) an LLM-based Rule Generator finetuned on four base models producing deployable Snort 2/3, Suricata, and YARA rules (average acceptance rate 96.2%), (iv) a Three-Phase Attack Reconstructor combining Louvain community detection, LLM-driven hypothesis generation, and Bayesian scoring (87.5% kill-chain accuracy), and (v) a layered Governance-MCP-Agentic AI-Security architecture where all tools are exposed via the Model Context Protocol, governed by an AI Governance Policy Engine with a two-layer guardrail pipeline (regex + Llama Prompt Guard 2 semantic classifier, achieving 98.1% F1 score with experimental zero false positives). Designed for Managed Security Service Providers, the platform supports multi-tenant isolation, role-based access, and fully local deployment. Finetuned anomaly and threat detectors achieve weighted F1 scores of 99.0% and 91.0%, respectively, in intrusion-detection benchmarks, running inferences in ≈21 ms with a machine-side mean time to detect of 1.58 s, and the rule generator exceeds 91% deployability on live IDS engines. A systematic comparison against eight SOC platforms confirms that LanG uniquely satisfies multiple industrial capabilities all in one open-source tool, while enforcing selected AI governance policies.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 25 of its 116 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

25 of 116 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024LLM Agents can Autonomously Hack Websites6 Feb

Other references · 24

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  4. 2023Mistral 7Bcited by 3,164
  5. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  7. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  8. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  9. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
  10. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  11. 2023Prompt Injection attack against LLM-integrated Applicationscited by 605
  12. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
12 more
  1. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 170
  2. 2018Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detectioncited by 121
  3. 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 96
  4. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 68
  5. 2022SecureBERT: A Domain-Specific Language Model for Cybersecuritycited by 60
  6. 2018HOLMES: Real-time APT Detection through Correlation of Suspicious Information Flowscited by 43
  7. 2023Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devicescited by 39
  8. 2023Beyond the Safeguards: Exploring the Security Risks of ChatGPTcited by 36
  9. 2024Large Language Models in Cybersecurity: State-of-the-Artcited by 34
  10. 2023LILAC: Log Parsing using LLMs with Adaptive Parsing Cachecited by 32
  11. 2023Log Parsing with Prompt-based Few-shot Learningcited by 29
  12. 2020A Multi-Vocal Review of Security Orchestrationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Connecting the Dots in Agentic AI Security: A Cross-Dimensional Threat Taxonomy, Evaluation Maturity, and Open Challengescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines
  2. 2026LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment
  3. 2026Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
  4. 2026AgentSOC: A Multi-Layer Agentic AI Framework for Security Operations Automation
  5. 2026A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
  6. 2026A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes
  7. 2025TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
  8. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures