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 neural networks (DNNs) have been deployed in safety-criticalsystems such as autonomous vehicles and medical devices. Shortly after that,the vulnerability of DNNs were revealed by stealthy adversarial examples wherecrafted inputs -- by adding tiny perturbations to original inputs -- can lead aDNN to generate misclassification outputs. To improve the robustness of DNNs,some algorithmic-based countermeasures against adversarial examples have beenintroduced thereafter.  In this paper, we propose a new type of stealthy attack on protected DNNs tocircumvent the algorithmic defenses: via smart bit flipping in DNN weights, wecan reserve the classification accuracy for clean inputs but misclassifycrafted inputs even with algorithmic countermeasures. To fool protected DNNs ina stealthy way, we introduce a novel method to efficiently find their mostvulnerable weights and flip those bits in hardware. Experimental results showthat we can successfully apply our stealthy attack against state-of-the-artalgorithmic-protected DNNs.

Stealthy Attack on Algorithmic-Protected DNNs via Smart Bit Flipping