LATIDIA · Investigación

Las redes neuronales de impulsos son más difíciles de robar: un estudio comparativo de ataques de robo de modelos.

arXiv:2610.36298v1 Announce Type: new Abstract: Los modelos de aprendizaje automático implementados detrás de las interfaces de consulta exponen más que sus predicciones, porque un adversario puede usar esas predicciones para reconstruir el modelo en sí. Mod

La noticia

arXiv:2610.36298v1 Announce Type: new Abstract: Machine learning models deployed behind query interfaces expose more than their predictions, because an adversary can use those predictions to rebuild the model itself. Model stealing attacks (MSAs) exploit this exposure by training a surrogate model that replicates the decision behavior of a target through black-box queries alone, without access to its parameters or training data. These attacks are well characterized for conventional artificial neural networks (ANNs), yet spiking neural networks (SNNs) process information in a fundamentally different way. SNNs communicate through sparse, discrete spikes, and their outputs depend on membrane potentials that evolve over time rather than on a static mapping from input to