Towards Verifying Robustness of Neural Networks Against Semantic Perturbations
This work addresses a critical gap in neural network verification for real-world adversarial attacks, offering a practical solution for improving security in domains like image classification, though it is incremental by building on existing verification tools.
The paper tackles the problem of verifying neural network robustness against semantic perturbations like color shifting and lighting adjustments, which existing methods struggle with, and proposes Semantify-NN, a model-agnostic approach that achieves superior verification performance over traditional methods, as demonstrated in experiments on various architectures and datasets.
Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the $\ell_p$-norm threat model of the input instances, robustness verification against semantic adversarial attacks inducing large $\ell_p$-norm perturbations, such as color shifting and lighting adjustment, are beyond their capacity. To bridge this gap, we propose \textit{Semantify-NN}, a model-agnostic and generic robustness verification approach against semantic perturbations for neural networks. By simply inserting our proposed \textit{semantic perturbation layers} (SP-layers) to the input layer of any given model, \textit{Semantify-NN} is model-agnostic, and any $\ell_p$-norm based verification tools can be used to verify the model robustness against semantic perturbations. We illustrate the principles of designing the SP-layers and provide examples including semantic perturbations to image classification in the space of hue, saturation, lightness, brightness, contrast and rotation, respectively. In addition, an efficient refinement technique is proposed to further significantly improve the semantic certificate. Experiments on various network architectures and different datasets demonstrate the superior verification performance of \textit{Semantify-NN} over $\ell_p$-norm-based verification frameworks that naively convert semantic perturbation to $\ell_p$-norm. The results show that \textit{Semantify-NN} can support robustness verification against a wide range of semantic perturbations. Code available https://github.com/JeetMo/Semantify-NN