LATIDIA · Ciberseguridad

Reflex-Guard: una barandilla de baja latencia para LLM Prompt Safety utilizando incrustaciones semánticas densas

arXiv: 2608.17556v2Tipo de anuncio: reemplazar Resumen: los modelos de lenguaje grandes (LLM) en aplicaciones del mundo real a menudo enfrentan los riesgos de indicaciones especialmente diseñadas diseñadas para eludir los controles de seguridad. La barandilla existente cumple

La noticia

arXiv:2608.17556v2 Announce Type: replace Abstract: Large Language Models (LLMs) in real-world applications often face the risks of specially crafted prompts designed to bypass the safety controls. Existing guardrail methods, such as LLM-as-a-judge and cloud-based safety APIs are able to detect unsafe content. However, they often add a delay of about 250-900 ms to each request. This delay is too high for real-time applications, when the system usually needs to respond in less than 100 ms. Furthermore, routing user prompts through external moderation endpoints raises significant data privacy concerns. This paper introduces Reflex-Guard, a lightweight guardrail that runs locally. It uses jailbreak-aware preprocessing, compact sentence-transformer embeddings, and seven fast binary classifiers.