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

Modern neural networks are highly non-robust against adversarialmanipulation. A significant amount of work has been invested in techniques tocompute lower bounds on robustness through formal guarantees and to buildprovably robust models. However, it is still difficult to get guarantees forlarger networks or robustness against larger perturbations. Thus attackstrategies are needed to provide tight upper bounds on the actual robustness.We significantly improve the randomized gradient-free attack for ReLU networks[9], in particular by scaling it up to large networks. We show that our attackachieves similar or significantly smaller robust accuracy than state-of-the-artattacks like PGD or the one of Carlini and Wagner, thus revealing anoverestimation of the robustness by these state-of-the-art methods. Our attackis not based on a gradient descent scheme and in this sense gradient-free,which makes it less sensitive to the choice of hyperparameters as no carefulselection of the stepsize is required.

Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks