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

Recently, there has been a rise in the development of powerful pre-trainednatural language models, including GPT-2, Grover, and XLM. These models haveshown state-of-the-art capabilities towards a variety of different NLP tasks,including question answering, content summarisation, and text generation.Alongside this, there have been many studies focused on online authorshipattribution (AA). That is, the use of models to identify the authors of onlinetexts. Given the power of natural language models in generating convincingtexts, this paper examines the degree to which these language models cangenerate texts capable of deceiving online AA models. Experimenting with bothblog and Twitter data, we utilise GPT-2 language models to generate texts usingthe existing posts of online users. We then examine whether these AI-based textgenerators are capable of mimicking authorial style to such a degree that theycan deceive typical AA models. From this, we find that current AI-based textgenerators are able to successfully mimic authorship, showing capabilitiestowards this on both datasets. Our findings, in turn, highlight the currentcapacity of powerful natural language models to generate original online postscapable of mimicking authorial style sufficiently to deceive popular AAmethods; a key finding given the proposed role of AA in real world applicationssuch as spam-detection and forensic investigation.

Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators