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

Transfer learning has become a common practice for training deep learningmodels with limited labeled data in a target domain. On the other hand, deepmodels are vulnerable to adversarial attacks. Though transfer learning has beenwidely applied, its effect on model robustness is unclear. To figure out thisproblem, we conduct extensive empirical evaluations to show that fine-tuningeffectively enhances model robustness under white-box FGSM attacks. We alsopropose a black-box attack method for transfer learning models which attacksthe target model with the adversarial examples produced by its source model. Tosystematically measure the effect of both white-box and black-box attacks, wepropose a new metric to evaluate how transferable are the adversarial examplesproduced by a source model to a target model. Empirical results show that theadversarial examples are more transferable when fine-tuning is used than theyare when the two networks are trained independently.

Two Sides of the Same Coin: White-box and Black-box Attacks for Transfer Learning