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 present a new type of backdoor attack that exploits a vulnerability ofconvolutional neural networks (CNNs) that has been previously unstudied. Inparticular, we examine the application of facial recognition. Deep learningtechniques are at the top of the game for facial recognition, which means theyhave now been implemented in many production-level systems. Alarmingly, unlikeother commercial technologies such as operating systems and network devices,deep learning-based facial recognition algorithms are not presently designedwith security requirements or audited for security vulnerabilities beforedeployment. Given how young the technology is and how abstract many of theinternal workings of these algorithms are, neural network-based facialrecognition systems are prime targets for security breaches. As more and moreof our personal information begins to be guarded by facial recognition (e.g.,the iPhone X), exploring the security vulnerabilities of these systems from apenetration testing standpoint is crucial. Along these lines, we describe ageneral methodology for backdooring CNNs via targeted weight perturbations.Using a five-layer CNN and ResNet-50 as case studies, we show that an attackeris able to significantly increase the chance that inputs they supply will befalsely accepted by a CNN while simultaneously preserving the error rates forlegitimate enrolled classes.

Backdooring Convolutional Neural Networks via Targeted Weight Perturbations