Towards verifying robustness of neural networks against a family of semantic perturbations
Name
1912.09533.pdf
Description
Accepted version
Size
1.55 MB
Format
Adobe PDF
Checksum (MD5)
53aec20192e28bd8ec9505ea32708018
Author(s)
Mohapatra, Jeet
Weng, Tsui-Wei
Chen, Pin-Yu
Liu, Sijia
Daniel, Luca
Date Issued
June 2020
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher
IEEE
Citation
Mohapatra, Jeet et al. “Towards verifying robustness of neural networks against a family of semantic perturbations.” Paper in the Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 13-19 June 2020, IEEE © 2020 The Author(s)
Version
Author's final manuscript
Abstract
Verifying robustness of neural networks given a specified threat model is a fundamental yet challenging task. While current verification methods mainly focus on the p-norm threat model of the input instances, robustness verification against semantic adversarial attacks inducing large p-norm perturbations, such as color shifting and lighting adjustment, are beyond their capacity. To bridge this gap, we propose Semantify-NN, a model-agnostic and generic robustness verification approach against semantic perturbations for neural networks. By simply inserting our proposed semantic perturbation layers (SP-layers) to the input layer of any given model, Semantify-NN is model-agnostic, and any 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 Semantify-NN over p-norm-based verification frameworks that naively convert semantic perturbation to p-norm. The results show that Semantify-NN can support robustness verification against a wide range of semantic perturbations.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR42600.2020.00032
