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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Machine learning has progressed significantly in various applications rangingfrom face recognition to text generation. However, its success has beenaccompanied by different attacks. Recently a new attack has been proposed whichraises both accountability and parasitic computing risks, namely the modelhijacking attack. Nevertheless, this attack has only focused on imageclassification tasks. In this work, we broaden the scope of this attack toinclude text generation and classification models, hence showing its broaderapplicability. More concretely, we propose a new model hijacking attack, Ditto,that can hijack different text classification tasks into multiple generationones, e.g., language translation, text summarization, and language modeling. Weuse a range of text benchmark datasets such as SST-2, TweetEval, AGnews, QNLI,and IMDB to evaluate the performance of our attacks. Our results show that byusing Ditto, an adversary can successfully hijack text generation modelswithout jeopardizing their utility.

Two-in-One: A Model Hijacking Attack Against Text Generation Models