Certified Robustness to Programmable Transformations in LSTMs
Yuhao Zhang, Aws Albarghouthi, Loris D’Antoni
Abstract
Deep neural networks for natural language processing are fragile in the face of adversarial examples—small input perturbations, like synonym substitution or word duplication, which cause a neural network to change its prediction. We present an approach to certifying the robustness of LSTMs (and extensions of LSTMs) and training models that can be efficiently certified. Our approach can certify robustness to intractably large perturbation spaces defined programmatically in a language of string transformations. Our evaluation shows that (1) our approach can train models that are more robust to combinations of string transformations than those produced using existing techniques; (2) our approach can show high certification accuracy of the resulting models.
BibTeX
@inproceedings{zhang-etal-2021-certified,
title = "Certified Robustness to Programmable Transformations in {LSTM}s",
author = "Zhang, Yuhao and
Albarghouthi, Aws and
D{'}Antoni, Loris",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.82/",
doi = "10.18653/v1/2021.emnlp-main.82",
pages = "1068--1083"
}