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/

Zendy Pro

Presents the zaia usage as premium feature

ZAIA

Presents AI Discovery search usage as a premium feature

AI Discovery

Presents AI Discovery explain and summary usage as a premium feature

Content Analysis

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Presents the pdf analysis as premium feature

PDF Analysis

1500 Top-up

3000 Top-up

Zendy Basic

2500 Top-up

Zendy Unlimited

Presents the access of premium content as premium feature

Premium Content

Adversarial attacks are carried out to reveal the vulnerability of deepneural networks. Textual adversarial attacking is challenging because text isdiscrete and a small perturbation can bring significant change to the originalinput. Word-level attacking, which can be regarded as a combinatorialoptimization problem, is a well-studied class of textual attack methods.However, existing word-level attack models are far from perfect, largelybecause unsuitable search space reduction methods and inefficient optimizationalgorithms are employed. In this paper, we propose a novel attack model, whichincorporates the sememe-based word substitution method and particle swarmoptimization-based search algorithm to solve the two problems separately. Weconduct exhaustive experiments to evaluate our attack model by attacking BiLSTMand BERT on three benchmark datasets. Experimental results demonstrate that ourmodel consistently achieves much higher attack success rates and crafts morehigh-quality adversarial examples as compared to baseline methods. Also,further experiments show our model has higher transferability and can bringmore robustness enhancement to victim models by adversarial training. All thecode and data of this paper can be obtained onhttps://github.com/thunlp/SememePSO-Attack.

Word-level Textual Adversarial Attacking as Combinatorial Optimization