LATIDIA · Investigación
REFORGE: Un método para evaluar comparativamente las capacidades de ingeniería inversa de los LLM en la denominación de funciones binarias descompiladas
arXiv:2607.07738v3 Tipo de anuncio: sustitución cruzada Resumen: Los grandes modelos de lenguaje (LLM) se aplican cada vez más a tareas de ingeniería inversa, y los informes recientes de inteligencia sobre amenazas muestran que operan dentro de ofertas activas.
WhatsApp ↗Telegram ↗
La noticia
arXiv:2607.07738v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to reverse-engineering tasks, and recent threat-intelligence reporting shows them operating inside live offensive-security workflows. Claims about their capability, however, outpace our ability to measure it. Existing benchmarks for LLM-assisted binary analysis treat the construction of function-level ground truth as a solved pre-processing step and report accuracy without disclosing how many functions were reliably evaluable. We argue that the principal obstacle to fair evaluation is not model capability but the reliability of binary-to-source alignment under compiler optimization. This paper presents Reforge, a provenance-tracked pipeline that constructs function-level ground truth from C source through compilation, DWARF and syntactic extraction, alignment,