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

We investigate to what extent alternative variants of Artificial NeuralNetworks (ANNs) are susceptible to adversarial attacks. We analyse theadversarial robustness of conventional, stochastic ANNs and Spiking NeuralNetworks (SNNs) in the raw image space, across three different datasets. Ourexperiments reveal that stochastic ANN variants are almost equally assusceptible as conventional ANNs when faced with simple iterativegradient-based attacks in the white-box setting. However we observe, that inblack-box settings, stochastic ANNs are more robust than conventional ANNs,when faced with boundary attacks, transferability and surrogate attacks.Consequently, we propose improved attacks and defence mechanisms for stochasticANNs in black-box settings. When performing surrogate-based black-box attacks,one can employ stochastic models as surrogates to observe higher attack successon both stochastic and deterministic targets. This success can be furtherimproved with our proposed Variance Mimicking (VM) surrogate training method,against stochastic targets. Finally, adopting a defender's perspective, weinvestigate the plausibility of employing stochastic switching of modelmixtures as a viable hardening mechanism. We observe that such a scheme doesprovide a partial hardening.

Exploring the Back Alleys: Analysing The Robustness of Alternative Neural Network Architectures against Adversarial Attacks