將CVE映射至MITRE ATT&CK技術：一個精心策劃的金標準集分類器與大型語言模型輔助標籤擴展的限制

摘要

我們提出了一套可重現的流程，能從自由文字格式的漏洞描述，將通用漏洞與暴露（CVE）映射至MITRE ATT&CK企業技術。此流程不依賴於CWE→CAPEC→ATT&CK的推導鏈（我們量化了該鏈中表格擴展所產生的偽影），而是在一份由MITRE威脅知情防禦中心專家所建立、包含1,207個CVE的優質黃金資料集上，訓練一個多標籤分類器。結果顯示，該模型在recall@5上約為零樣本嵌入相似度基線的兩倍，且所有排序指標均有所提升。隨後，我們探討是否可藉助大語言模型輔助標註來擴展黃金資料集。初步實驗呈現矛盾結論：單次實驗顯示效能下降，而對五個隨機種子取平均則顯示小幅提升。然而，經獨立重複驗證及擴展規模研究（增加100至984個CVE）後發現，表面上的改善其實是評估偽影所致。大語言模型生成的標籤與專家標註的一致率約為0.39，在任一擴展規模下均無法提供可靠的改善，且在約新增1,000個CVE時，稀有技術的覆蓋率反而下降（macro-F1降低0.04）。根本原因在於評估雜訊。若在小型測試集上選取檢查點，實質上相當於在多個帶雜訊的評估中最大化結果，導致原本相同的實驗之間recall@5差異可達0.05。根據基於驗證集檢查點選取的正確流程，僅使用黃金資料的模型recall@5為（0.673 ± 0.019）；重複關鍵實驗後，確認大語言模型擴展並無顯著效果。最終的規模擴展研究顯示，加入更多專家策劃的資料能持續提升效能，但加入大語言模型標註的資料則否，這表明分類器的限制來自標籤品質而非資料規模。所有資料集、模型、程式碼及訓練記錄均已公開釋出。

English

We present a reproducible pipeline for mapping Common Vulnerabilities and Exposures (CVEs) to MITRE ATT&CK Enterprise techniques from free-text vulnerability descriptions. Rather than relying on the CWE->CAPEC->ATT&CK derivation chain, whose table-expansion artifacts we quantify, we train a multi-label classifier on a curated gold dataset of 1,207 CVEs from expert MITRE Center for Threat-Informed Defense mappings. The resulting model approximately doubles recall@5 compared with a zero-shot embedding-similarity baseline and improves every ranking metric. We then investigate whether LLM-assisted labeling can extend the gold dataset. Initial experiments suggest contradictory conclusions: a single run indicates degraded performance, while averaging over five random seeds suggests a small gain. However, an independent replication and an expansion-size study (100--984 additional CVEs) show that the apparent improvement is an evaluation artifact. LLM-generated labels, with approximately 0.39 agreement with expert annotations, provide no reliable improvement at any expansion size and reduce rare-technique coverage at around 1,000 added CVEs (macro-F1 decreases by 0.04). The root cause is evaluation noise. Selecting checkpoints on a small test split effectively maximizes over many noisy evaluations, producing recall@5 differences of up to 0.05 between otherwise identical runs. Using a corrected protocol based on validation-split checkpoint selection, the gold-only model achieves recall@5 of (0.673 \pm 0.019), and repeating the decisive experiment confirms the null result for LLM expansion. A final scaling study shows that additional expert-curated data consistently improves performance, whereas LLM-labeled data does not, indicating that the classifier is limited by label quality rather than dataset size. All datasets, models, code, and training logs are publicly released.