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

Online texts with toxic content are a threat in social media that might causecyber harassment. Although many platforms applied measures, such as machinelearning-based hate-speech detection systems, to diminish their effect, thosetoxic content publishers can still evade the system by modifying the spellingof toxic words. Those modified words are also known as human-written textperturbations. Many research works developed certain techniques to generateadversarial samples to help the machine learning models obtain the ability torecognize those perturbations. However, there is still a gap between thosemachine-generated perturbations and human-written perturbations. In this paper,we introduce a benchmark test set containing human-written perturbations onlinefor toxic speech detection models. We also recruited a group of workers toevaluate the quality of this test set and dropped low-quality samples.Meanwhile, to check if our perturbation can be normalized to its clean version,we applied spell corrector algorithms on this dataset. Finally, we test thisdata on state-of-the-art language models, such as BERT and RoBERTa, and blackbox APIs, such as perspective API, to demonstrate the adversarial attack withreal human-written perturbations is still effective.

NoisyHate: Benchmarking Content Moderation Machine Learning Models with Human-Written Perturbations Online