LATIDIA · Ciberseguridad
Detección autónoma de amenazas de OSS a través de LLM alineados con la taxonomía
arXiv: 2610.01263v2Tipo de anuncio: reemplazar Resumen: Los ecosistemas de software de código abierto (OSS) se enfrentan a amenazas crecientes en la cadena de suministro, incluyendo typosquatting, confusión de dependencias, ofuscación de fuentes troyanas, construcción maliciosa
WhatsApp ↗Telegram ↗
La noticia
arXiv:2610.01263v2 Announce Type: replace Abstract: Open-source software (OSS) ecosystems face escalating supply chain threats, including typosquatting, dependency confusion, Trojan Source obfuscation, malicious build injection, and CI/CD pipeline poisoning. Sonatype documented over 1.2 million cumulative malicious packages across major registries, while signature-based and rule-based detection approaches lack the semantic understanding needed to generalize across evolving attacks. This paper proposes a taxonomy-aligned large language model framework for automated detection and multi-class classification of OSS supply chain threats. We introduce an AV-xxx taxonomy covering five semantically distinct attack categories and curate 999 verified real-world incidents from GitHub Security Advisories, CISA alerts, government security databases, and commercial threat intelligence reports, spanning 2018 to 2026