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

Deep Neural Networks (DNNs) are employed in an increasing number ofapplications, some of which are safety critical. Unfortunately, DNNs are knownto be vulnerable to so-called adversarial attacks that manipulate inputs tocause incorrect results that can be beneficial to an attacker or damaging tothe victim. Multiple defenses have been proposed to increase the robustness ofDNNs. In general, these defenses have high overhead, some requireattack-specific re-training of the model or careful tuning to adapt todifferent attacks.  This paper presents HASI, a hardware-accelerated defense that uses a processwe call stochastic inference to detect adversarial inputs. We show that bycarefully injecting noise into the model at inference time, we candifferentiate adversarial inputs from benign ones. HASI uses the outputdistribution characteristics of noisy inference compared to a non-noisyreference to detect adversarial inputs. We show an adversarial detection rateof 86% when applied to VGG16 and 93% when applied to ResNet50, which exceedsthe detection rate of the state of the art approaches, with a much loweroverhead. We demonstrate two software/hardware-accelerated co-designs, whichreduces the performance impact of stochastic inference to 1.58X-2X relative tothe unprotected baseline, compared to 15X-20X overhead for a software-only GPUimplementation.

HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks