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

The exponential growth of social media platforms has brought about arevolution in communication and content dissemination in human society.Nevertheless, these platforms are being increasingly misused to spread toxiccontent, including hate speech, malicious advertising, and pornography, leadingto severe negative consequences such as harm to teenagers' mental health.Despite tremendous efforts in developing and deploying textual and imagecontent moderation methods, malicious users can evade moderation by embeddingtexts into images, such as screenshots of the text, usually with someinterference. We find that modern content moderation software's performanceagainst such malicious inputs remains underexplored. In this work, we proposeOASIS, a metamorphic testing framework for content moderation software. OASISemploys 21 transform rules summarized from our pilot study on 5,000 real-worldtoxic contents collected from 4 popular social media applications, includingTwitter, Instagram, Sina Weibo, and Baidu Tieba. Given toxic textual contents,OASIS can generate image test cases, which preserve the toxicity yet are likelyto bypass moderation. In the evaluation, we employ OASIS to test fivecommercial textual content moderation software from famous companies (i.e.,Google Cloud, Microsoft Azure, Baidu Cloud, Alibaba Cloud and Tencent Cloud),as well as a state-of-the-art moderation research model. The results show thatOASIS achieves up to 100% error finding rates. Moreover, through retraining themodels with the test cases generated by OASIS, the robustness of the moderationmodel can be improved without performance degradation.

An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software