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

Recently, deep learning based natural language processing techniques arebeing extensively used to deal with spam mail, censorship evaluation in socialnetworks, among others. However, there is only a couple of works evaluating thevulnerabilities of such deep neural networks. Here, we go beyond attacks toinvestigate, for the first time, universal rules, i.e., rules that are sampleagnostic and therefore could turn any text sample in an adversarial one. Infact, the universal rules do not use any information from the method itself (noinformation from the method, gradient information or training datasetinformation is used), making them black-box universal attacks. In other words,the universal rules are sample and method agnostic. By proposing acoevolutionary optimization algorithm we show that it is possible to createuniversal rules that can automatically craft imperceptible adversarial samples(only less than five perturbations which are close to misspelling are insertedin the text sample). A comparison with a random search algorithm furtherjustifies the strength of the method. Thus, universal rules for foolingnetworks are here shown to exist. Hopefully, the results from this work willimpact the development of yet more sample and model agnostic attacks as well astheir defenses, culminating in perhaps a new age for artificial intelligence.

Universal Rules for Fooling Deep Neural Networks based Text Classification