LATIDIA · Ciberseguridad

GuidedRay: descubrimiento de direcciones guiadas por la diversidad para ataques de cajas negras de etiqueta dura dirigidos

arXiv:2609.25734v1 Tipo de anuncio: nuevo Resumen: Las redes neuronales profundas son vulnerables a los ataques adversarios. Entre los ataques de caja negra, los ataques dirigidos basados en decisiones son particularmente difíciles: el atacante solo observa

La noticia

arXiv:2609.25734v1 Announce Type: new Abstract: Deep neural networks are vulnerable to adversarial attacks. Among black-box attacks, targeted decision-based attacks are particularly difficult: the attacker observes only the target model's top-1 label and aims to make it predict a prespecified target class under a bounded perturbation. Before perturbation refinement, the attacker must discover a direction that reaches the prescribed target region. This initialization step can incur substantial query cost. We propose GuidedRay, a targeted decision-based attack based on diversity-guided direction discovery. GuidedRay builds on two observations: target-class reference samples provide useful target-conditioned direction priors, and diverse candidates increase the probability of discovering a targeted adversarial direction. GuidedRay generates varied candidates from