LATIDIA · Ciberseguridad

LLM Ghostbusters: paquete quirúrgico de supresión de alucinaciones a través del desaprendizaje adaptativo

arXiv: 2605.01047v2Tipo de anuncio: reemplazar Resumen: Las alucinaciones siguen siendo un problema no resuelto para los LLM, y las alucinaciones del paquete son un ejemplo particularmente peligroso de este fenómeno. Las alucinaciones del paquete ocurren du

La noticia

arXiv:2605.01047v2 Announce Type: replace Abstract: Hallucinations remain an unsolved problem for LLMs, and package hallucinations are a particularly dangerous instance of this phenomenon. Package hallucinations occur during code generation when a model fabricates non-existent software packages, recommending imports and installation commands for fictional libraries. This creates a critical supply-chain vulnerability; an attacker can proactively register such packages on public registries with malicious payloads that are subsequently installed and executed by developers or autonomous agents. These hallucinations enable a class of package confusion attack known as slopsquatting. To address this issue, we present Adaptive Unlearning (AU), a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility. AU introduces