TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Text
Ahmed Lekssays, Utsav Shukla, Hüsrev Taha Sencar, Md Rizwan Parvez · 2025
Accurately identifying adversarial techniques in security texts is critical for effective cyber defense.However, existing methods face a fundamental trade-off: they either rely on generic models with limited domain precision or require resource-intensive pipelines that depend on large labeled datasets and task-specific optimizations-such as custom hard-negative mining and denoising-resources rarely available in specialized domains.We propose TECHNIQUERAG, a domain-specific retrievalaugmented generation (RAG) framework that bridges this gap by integrating off-the-shelf retrievers, instruction-tuned LLMs, and minimal text-technique pairs.First, our approach mitigates data scarcity by fine-tuning only the generation component on limited in-domain examples, circumventing resource-intensive retrieval training.Second, although conventional RAG mitigates hallucination by coupling retrieval and generation, its dependence on generic retrievers often introduces noisy candidates, thereby limiting domain-specific precision.To address, we enhance the retrieval quality and domain specificity through a zero-shot LLM re-ranking that explicitly aligns retrieved candidates with adversarial techniques.Experiments on multiple security benchmarks demonstrate that TECHNIQUERAG achieves state-of-the-art performances without extensive task-specific optimizations or labeled data, while comprehensive analysis provides further insights.