English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep learning models have achieved great success in many fields, yet they arevulnerable to adversarial examples. This paper follows a causal perspective tolook into the adversarial vulnerability and proposes Causal Intervention bySemantic Smoothing (CISS), a novel framework towards robustness against naturallanguage attacks. Instead of merely fitting observational data, CISS learnscausal effects p(y|do(x)) by smoothing in the latent semantic space to makerobust predictions, which scales to deep architectures and avoids tediousconstruction of noise customized for specific attacks. CISS is provably robustagainst word substitution attacks, as well as empirically robust even whenperturbations are strengthened by unknown attack algorithms. For example, onYELP, CISS surpasses the runner-up by 6.7% in terms of certified robustnessagainst word substitutions, and achieves 79.4% empirical robustness whensyntactic attacks are integrated.

Certified Robustness Against Natural Language Attacks by Causal Intervention