From Context to Rules: Toward Unified Detection Rule Generation
For practitioners needing to generate detection rules across diverse contexts and languages, this work provides a unified approach that eliminates the need for separate pipelines.
The paper formalizes detection rule generation as a unified mapping problem and proposes UniRule, an agentic RAG framework using dual semantic projection spaces. Experiments across 12 scenarios show UniRule outperforms pure LLM generation with a Bradley-Terry coefficient of 0.52.
Existing methods for detection rule generation are tightly coupled to specific input-output combinations, requiring dedicated pipelines for each. We formalize this problem as a unified mapping f:C*L->R and characterize optimal rules through semantic distance. We propose UniRule, an agentic RAG framework built on dual semantic projection spaces: detection intent and detection logic. This design enables retrieval and generation across arbitrary contexts and target languages within a single system. Experiments across 12 scenarios (3 languages, 4 context types, 12,000 pairwise comparisons) show that UniRule significantly outperforms pure LLM generation with a Bradley-Terry coefficient of 0.52, validating semantic projection as an effective abstraction for unified rule generation. Together, the formalization, method, and evaluation provide an initial framework for studying detection rule generation as a unified task.