Certified Robustness Against Natural Language Attacks by Causal Intervention

Haiteng Zhao · Chang Ma · Xinshuai Dong · Anh Tuan Luu · Zhi-Hong Deng · Hanwang Zhang

Room 301 - 303
[ Abstract ] [ Livestream: Visit APP: Language, Speech and Dialog ]
Tue 19 Jul 7:30 a.m. — 7:35 a.m. PDT
[ Paper PDF

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 6.8% in terms of certified robustness against word substitutions, and achieves 80.7% empirical robustness when syntactic attacks are integrated.

Chat is not available.