LATIDIA · Ciberseguridad

La fragilidad de los mecanismos de activación-etiqueta para la detección de uso indebido en LLM de peso abierto

arXiv: 2610.03124v1Tipo de anuncio: nuevo Resumen: los modelos de lenguaje de peso abierto se pueden descargar, modificar e implementar fuera del control de sus desarrolladores, lo que limita la efectividad de las salvaguardas aplicadas de forma centralizada. Reciente

La noticia

arXiv:2610.03124v1 Announce Type: new Abstract: Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforced safeguards. Recent work has therefore proposed \emph{trigger-tag} mechanisms that produce a detectable signal when a model is used under a target condition, such as generating phishing contents. Although these mechanisms borrow from established techniques, their use for conditional misuse detection in open-weight LLMs is relatively new. Therefore, existing research works have not systematically studied the robustness of trigger-tag mechanisms under adversarial attacks. To close this gap, (i)~we formalize trigger-tags and distinguish \emph{token-level trigger-tags}, which introduce watermark-inspired signals during decoding, from \emph{weight-level trigger-tags}, which learn backdoor-inspired associations