SOURCE-LINKED INTELLIGENCE

Implementing a White-Box Undetectable Backdoor for Random Fourier Features

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorithm, under a hardness assumption tied to the Continuous Learning With Errors (CLWE) problem. Under standard cryptographic assumptions, even a full white-box audit of a model's weights cannot detect this class of backdoor. The construction is stated in terms of cryptographic reductions and probabilistic lemmas, without a reference implementation, and relies on secondary machinery such as the Sparse Gaussian Pancakes distribution and a homogeneous CL

Read original source ↗ Open in workspace

recordType

paper

region

Global