Certified Robustness Against Natural Language Attacks by Causal Intervention

05/24/2022
by   Haiteng Zhao, et al.
0

Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversarial vulnerability and proposes Causal Intervention by Semantic Smoothing (CISS), a novel framework towards robustness against natural language attacks. Instead of merely fitting observational data, CISS learns causal effects p(y|do(x)) by smoothing in the latent semantic space to make robust predictions, which scales to deep architectures and avoids tedious construction of noise customized for specific attacks. CISS is provably robust against word substitution attacks, as well as empirically robust even when perturbations are strengthened by unknown attack algorithms. For example, on YELP, CISS surpasses the runner-up by 6.7 against word substitutions, and achieves 79.4 syntactic attacks are integrated.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/17/2021

Adversarial Visual Robustness by Causal Intervention

Adversarial training is the de facto most promising defense against adve...
research
07/31/2023

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks

The language models, especially the basic text classification models, ha...
research
05/25/2023

IDEA: Invariant Causal Defense for Graph Adversarial Robustness

Graph neural networks (GNNs) have achieved remarkable success in various...
research
09/15/2021

BERT is Robust! A Case Against Synonym-Based Adversarial Examples in Text Classification

Deep Neural Networks have taken Natural Language Processing by storm. Wh...
research
06/11/2021

Adversarial Robustness through the Lens of Causality

The adversarial vulnerability of deep neural networks has attracted sign...
research
02/09/2019

When Causal Intervention Meets Adversarial Examples and Image Masking for Deep Neural Networks

Discovering and exploiting the causality in deep neural networks (DNNs) ...
research
02/09/2019

When Causal Intervention Meets Image Masking and Adversarial Perturbation for Deep Neural Networks

Discovering and exploiting the causality in deep neural networks (DNNs) ...

Please sign up or login with your details

Forgot password? Click here to reset