LATIDIA · Ciberseguridad

GuardrailAgent: un marco agénico para la defensa contra el jailbreak

arXiv: 2611.09734v1Tipo de anuncio: nuevo Resumen: A pesar de recibir capacitación en seguridad para alinearse con los valores humanos, los modelos de lenguaje grandes (LLM) siguen siendo vulnerables a los ataques de jailbreak que eluden las salvaguardas incorporadas y e

La noticia

arXiv:2611.09734v1 Announce Type: new Abstract: Despite undergoing safety training to align with human values, large language models (LLMs) remain vulnerable to jailbreak attacks that circumvent built-in safeguards and elicit malicious behaviors given by the adversary. Existing defenses are mostly static and fail to adapt to new or unknown attack strategies, providing limited resilience. To address these, we propose a multi-agent defense framework, GuardrailAgent, that offers adaptive, end-to-end protection. The system autonomously gathers and summarizes attack characteristics into a continuously updated knowledge base that supports both input- and output-side detection. A feedback module integrates misclassified cases for iterative improvement at minimal cost. Tested on over ten representative jailbreaks, the framework achieved