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

Security of inference phase deployment of Convolutional neural network (CNN)into resource constrained embedded systems (e.g. low end FPGAs) is a growingresearch area. Using secure practices, third party FPGA designers can beprovided with no knowledge of initial and final classification layers. In thiswork, we demonstrate that hardware intrinsic attack (HIA) in such a "secure"design is still possible. Proposed HIA is inserted inside mathematicaloperations of individual layers of CNN, which propagates erroneous operationsin all the subsequent CNN layers that lead to misclassification. The attack isnon-periodic and completely random, hence it becomes difficult to detect. Fivedifferent attack scenarios with respect to each CNN layer are designed andevaluated based on the overhead resources and the rate of triggering incomparison to the original implementation. Our results for two CNNarchitectures show that in all the attack scenarios, additional latency isnegligible (<0.61%), increment in DSP, LUT, FF is also less than 2.36%. Threeattack scenarios do not require any additional BRAM resources, while in twoscenarios BRAM increases, which compensates with the corresponding decrease inFF and LUTs. To the authors' best knowledge this work is the first to addressthe hardware intrinsic CNN attack with the attacker does not have knowledge ofthe full CNN.

SoWaF: Shuffling of Weights and Feature Maps: A Novel Hardware Intrinsic Attack (HIA) on Convolutional Neural Network (CNN)