CTI-REALM

Inspect AI agent benchmark where a model writes Sigma and KQL detection rules from cyber threat intelligence reports against live Kusto telemetry.

Also known as: CTI REALM, Cyber Threat Real World Evaluation and LLM Benchmarking

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categoryagentic
Subcategoryagentic detection-rule writing from CTI reports against Kusto telemetry
Page statusactive
Metricweighted trajectory reward R_total in [0, 1]
Directionhigher_is_better
Dataset size50
Dataset licenceMIT (inspect_evals package and CTI_REALM_TRANSPARENCY.md); Hugging Face dataset licence not stated
PublisherMicrosoft Security AI (inspect_evals packaging by UK AI Security Institute)

What it measures

CTI-REALM (Cyber Threat Real World Evaluation and LLM Benchmarking) tests whether an AI agent can turn a detection objective and public CTI reports into working detections. The agent must find a relevant report, map MITRE ATT&CK techniques, explore Kusto tables, write and run KQL, and emit a Sigma rule plus query results as JSON. The environment is a Docker stack with a shared Kusto emulator, 12 log sources, 37 CTI reports, and cached MITRE and Sigma stores. Attacks are emulated on Linux endpoints, Azure Kubernetes Service (AKS), and Azure cloud. Scoring is a five-checkpoint trajectory reward in [0, 1], not a static multiple-choice grade. This page treats it as agentic because success depends on tool use against live telemetry.

Task format

ReAct agent, English. inspect_evals defaults: message_limit 70, one epoch, hard difficulty (minimal workflow hints). Output must be JSON with sigma_rule, kql_query, and query_results. Tools include Kusto query/schema helpers, CTI retrieval, MITRE lookup, and Sigma lookup. bash and python run in a per-sample sandbox without Kusto network access. Four tasks: cti_realm_25, cti_realm_50, cti_realm_25_minimal (CTI tools removed), cti_realm_25_seeded (workflow files in /memories/).

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub