LATIDIA · Ciberseguridad

FragToken: amplificación de los costes de inferencia de LLM a través de la generación de tokens no canónicos

arXiv: 2609.31552v1Tipo de anuncio: nuevo Resumen: A medida que la inferencia del modelo de lenguaje grande (LLM) se vuelve cada vez más costosa, los ataques de consumo de recursos representan una amenaza creciente para los proveedores de modelos. Los ataques existentes suelen ser

La noticia

arXiv:2609.31552v1 Announce Type: new Abstract: As large language model (LLM) inference becomes increasingly expensive, resource-consumption attacks pose a growing threat to model providers. Existing attacks typically amplify cost by inducing abnormally long or repetitive outputs on attacker-controlled or triggered requests, making them easier to detect and limiting their deployment-wide impact when benign traffic dominates. In this work, we uncover a previously overlooked token-level attack surface arising from the many-to-one mapping from token sequences to decoded text. Although standard LLMs predominantly generate the canonical token sequences induced by their tokenizers, the same text can also be represented by substantially longer non-canonical sequences. This representational flexibility exposes a new avenue for resource-consumption