LATIDIA · Ciberseguridad

Todo el mundo es un poco racista: un nuevo ataque de puerta trasera ML en modo de caja negra

arXiv: 2610.22459v1Tipo de anuncio: nuevo Resumen: Las puertas traseras se encuentran entre los ataques más impactantes contra el aprendizaje automático (ML), sin embargo, la mayoría de los métodos existentes asumen alguna forma de envenenamiento por tiempo de entrenamiento o manipulación directa del modelo

La noticia

arXiv:2610.22459v1 Announce Type: new Abstract: Backdoors are among the most impactful attacks against Machine Learning (ML), yet most existing methods assume some form of training-time poisoning or direct model manipulation. This is often considered sufficient to assume that existing systems are not exposed to actual risks. In this paper, we introduce Backdoor-as-a-Service, a model-agnostic, fully black-box technique that, instead of installing a backdoor, activates it in the form of a latent secondary task leveraging on an already present behavior. Our tool uses genetic search to discover input transformations that induce systematic output differences aligned with an attacker-defined task, without modifying training data, architecture, or weights. We verify our approach against