Certified Robustness to Programmable Transformations in LSTMs

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.

arXiv commentEMNLP 2021

References in corpus (5)

• Certified Adversarial Robustness via Randomized Smoothing
• Efficient Neural Network Robustness Certification with General Activation Functions
• Towards Robustness Against Natural Language Word Substitutions
• POPQORN: Quantifying Robustness of Recurrent Neural Networks
• Robustness Verification for Transformers