Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures

arXiv:2403.14772v1 Announce Type: cross
Abstract: Recent model inversion attack algorithms permit adversaries to reconstruct a neural network's private training data just by repeatedly querying the network and inspecting its outputs. In this work, we develop a novel network architecture that leverages sparse-coding layers to obtain superior robustness to this class of attacks. Three decades of computer science research has studied sparse coding in the context of image denoising, object recognition, and adversarial misclassification settings, but to the best of our …

abstract algorithms architecture architectures arxiv attacks class coding cs.ai cs.cr cs.cv cs.lg data improving network network architecture neural network novel robustness training training data type via work