Certified Robustness from Approximate Gaussian Mixture Structures in Pretrained Latent Spaces

ArXi:2605.25352v1 Announce Type: cross Deep learning models are vulnerable to adversarial perturbations, raising important concerns for safety-critical deployment. Empirical defenses can achieve strong robustness in practice, but lack formal guarantees, motivating the need for certifiably robust classifiers. While certified methods provide formal guarantees, they often yield overly conservative bounds due to their inability to exploit structure in complex data distributions.