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

The prediction accuracy has been the long-lasting and sole standard forcomparing the performance of different image classification models, includingthe ImageNet competition. However, recent studies have highlighted the lack ofrobustness in well-trained deep neural networks to adversarial examples.Visually imperceptible perturbations to natural images can easily be craftedand mislead the image classifiers towards misclassification. To demystify thetrade-offs between robustness and accuracy, in this paper we thoroughlybenchmark 18 ImageNet models using multiple robustness metrics, including thedistortion, success rate and transferability of adversarial examples between306 pairs of models. Our extensive experimental results reveal several newinsights: (1) linear scaling law - the empirical $\ell_2$ and $\ell_\infty$distortion metrics scale linearly with the logarithm of classification error;(2) model architecture is a more critical factor to robustness than model size,and the disclosed accuracy-robustness Pareto frontier can be used as anevaluation criterion for ImageNet model designers; (3) for a similar networkarchitecture, increasing network depth slightly improves robustness in$\ell_\infty$ distortion; (4) there exist models (in VGG family) that exhibithigh adversarial transferability, while most adversarial examples crafted fromone model can only be transferred within the same family. Experiment code ispublicly available at \url{https://github.com/huanzhang12/Adversarial_Survey}.

Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models