ZeroHour
arXiv cs.CRpublished ()ingested Akash Prakash

Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports

infoResearchimportance 45
AI summary · glm-5.3-flash

AHLERT generates environment-aware threat hunting leads from CTI reports using ATT&CK-seeded knowledge graph retrieval, roughly doubling F1 over flat-RAG baselines.

The paper introduces AHLERT, a system that converts Cyber Threat Intelligence reports into structured, investigable hunt leads via hybrid dense retrieval with multi-hop traversal over an MITRE ATT&CK-seeded knowledge graph and ontology-grounded RAG constrained to the defender's assets. It is LLM-agnostic and evaluated on public CTI reports for well-known APTs across proprietary and open-weight models. Hybrid evidence retrieval with ontology grounding raises mean F1 from 0.44 to 0.85, and AHLERT attains the highest effectiveness score (~86.95%) versus off-the-shelf LLMs.

  • Hybrid dense retrieval plus multi-hop graph traversal seeded with MITRE ATT&CK
  • Ontology grounding constrains leads to the defender's own assets and controls
  • Mean F1 rises from 0.44 to 0.85 versus flat-RAG baseline
  • Achieves ~86.95% effectiveness across proprietary and open-weight LLMs
VendorsMITRE
OrganizationsMITRE
Full article179 words · extracted from arxiv.org · click to collapse

Threat hunting increasingly depends on converting unstructured knowledge (e.g., Cyber Threat Intelligence reports) into actionable hunt leads: concise, investigable hypotheses grounded in observable artifacts and adversary techniques. Producing such leads manually is a tedious and hard-to-scale task. Existing automated approaches stop at the entity layer, ignore the defender's operational environment, and analyze each report in isolation. To address these gaps, we introduce AHLERT, a system that automatically extracts relevant, environment-aware, and hunt leads from threat reports through (i) a hybrid retriever that combines dense vector search with multi-hop traversal over a knowledge graph seeded with MITRE ATT&CK; (ii) an ontology-grounding retrieval-augmented generation method that constrains each lead to the defender's own assets and controls; and (iii) an LLM-agnostic framework that emits structured, directly actionable leads rather than loose indicators of compromise. We evaluate AHLERT on public CTI reports for well-known APTs across multiple proprietary and open-weight models. Hybrid evidence retrieval with ontology grounding raises mean F1 by ~2x (0.44 to 0.85) over a single-route flat-RAG baseline, and AHLERT attains the highest effectiveness score (~86.95%) compared with off-the-shelf LLM models.

Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.08790