{"ID":6138338,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-11T15:55:22.600961252Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.07573","arxiv_id":"2607.07573","title":"Multi-Class vs. Multi-Label BERT for CVE-to-CWE Mapping: How Taxonomy Structure Shapes the Errors","abstract":"Assigning Common Weakness Enumeration (CWE) categories to Common Vulnerabilities and Exposures (CVE) records remains an important but largely manual step in vulnerability analysis. We study this task as a text classification problem and compare two modelling choices: a \\emph{multi-class} formulation that predicts a single CWE per CVE and a \\emph{multi-label} formulation that allows multiple assignments. Three transformer encoders (BERT Base, SecureBERT, and CySecBERT) are evaluated on three nested label spaces (83, 47, and 25 classes). Multi-class training achieves higher macro-F1 across all settings, although the gap to multi-label narrows from 21 to 2 percentage points as the label space shrinks. Post-hoc threshold optimisation on the multi-label side closes this gap on the 25-class setting. Confusion analysis shows that the dominant misclassification patterns follow the CWE hierarchy and are shared across all three encoders (Pearson $r \u003e 0.92$), which suggests that the error structure is driven more by taxonomy design than by encoder choice. A hierarchy-relaxed evaluation that forgives within-family confusions raises macro-F1 from ${\\sim}$81\\% to ${\\sim}$90\\%, indicating that strict metrics understate branch-level classifier quality. CySecBERT achieves the strongest results overall, with statistically significant gains concentrated in the multi-label setting.","short_abstract":"Assigning Common Weakness Enumeration (CWE) categories to Common Vulnerabilities and Exposures (CVE) records remains an important but largely manual step in vulnerability analysis. We study this task as a text classification problem and compare two modelling choices: a \\emph{multi-class} formulation that predicts a sin...","url_abs":"https://arxiv.org/abs/2607.07573","url_pdf":"https://arxiv.org/pdf/2607.07573v1","authors":"[\"Ana Schwengber Kelm\",\"Christian Bockermann\",\"Jörg Frochte\"]","published":"2026-07-08T16:01:21Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CR\"]","methods":"[\"Transformer\"]","has_code":false}