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 Plus

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

Zendy Tools

Zendy Open

As the pre-trained language models (PLMs) continue to grow, so do thehardware and data requirements for fine-tuning PLMs. Therefore, the researchershave come up with a lighter method called \textit{Prompt Learning}. However,during the investigations, we observe that the prompt learning methods arevulnerable and can easily be attacked by some illegally constructed prompts,resulting in classification errors, and serious security problems for PLMs.Most of the current research ignores the security issue of prompt-basedmethods. Therefore, in this paper, we propose a malicious prompt templateconstruction method (\textbf{PromptAttack}) to probe the security performanceof PLMs. Several unfriendly template construction approaches are investigatedto guide the model to misclassify the task. Extensive experiments on threedatasets and three PLMs prove the effectiveness of our proposed approachPromptAttack. We also conduct experiments to verify that our method isapplicable in few-shot scenarios.

PromptAttack: Prompt-based Attack for Language Models via Gradient Search