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

Since the training data for the target model in a data-free black-box attackis not available, most recent schemes utilize GANs to generate data fortraining substitute model. However, these GANs-based schemes suffer from lowtraining efficiency as the generator needs to be retrained for each targetmodel during the substitute training process, as well as low generationquality. To overcome these limitations, we consider utilizing the diffusionmodel to generate data, and propose a data-free black-box attack scheme basedon diffusion model to improve the efficiency and accuracy of substitutetraining. Despite the data generated by the diffusion model exhibits highquality, it presents diverse domain distributions and contains many samplesthat do not meet the discriminative criteria of the target model. To furtherfacilitate the diffusion model to generate data suitable for the target model,we propose a Latent Code Augmentation (LCA) method to guide the diffusion modelin generating data. With the guidance of LCA, the data generated by thediffusion model not only meets the discriminative criteria of the target modelbut also exhibits high diversity. By utilizing this data, it is possible totrain substitute model that closely resemble the target model more efficiently.Extensive experiments demonstrate that our LCA achieves higher attack successrates and requires fewer query budgets compared to GANs-based schemes fordifferent target models.

Data-free Black-box Attack based on Diffusion Model