# Causal Interpretability for Adversarial Robustness: A Hybrid Generative Classification Approach Source: [Causal Interpretability for Adversarial Robustness: A Hybrid Generative Classification Approach]() Collection index: [llms.txt]() Data updated: 2025-12-10T05:01:26.267Z Authors: Chunheng Zhao, Pierluigi Pisu, Gurcan Comert, Negash Begashaw, Varghese Vaidyan, Nina Christine Hubig Published: 2024-12-28T05:06:20.000Z ## Abstract Deep learning-based discriminative classifiers, despite their remarkable success, remain vulnerable to adversarial examples that can mislead model predictions. While adversarial training can enhance robustness, it fails to address the intrinsic vulnerability stemming from the opaque nature of these black-box models. We present a deep ensemble model that combines discriminative features with generative models to achieve both high accuracy and adversarial robustness. Our approach integrates a bottom-level pre-trained discriminative network for feature extraction with a top-level generative classification network that models adversarial input distributions through a deep latent variable model. Using variational Bayes, our model achieves superior robustness against white-box adversarial attacks without adversarial training. Extensive experiments on CIFAR-10 and CIFAR-100 demonstrate our model's superior adversarial robustness. Through evaluations using counterfactual metrics and feature interaction-based metrics, we establish correlations between model interpretability and adversarial robustness. Additionally, preliminary results on Tiny-ImageNet validate our approach's scalability to more complex datasets, offering a practical solution for developing robust image classification models. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()