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

The convolutional neural network is the crucial tool for the recent successof deep learning based methods on various computer vision tasks likeclassification, segmentation, and detection. Convolutional neural networksachieved state-of-the-art performance in these tasks and every day pushing thelimit of computer vision and AI. However, adversarial attack on computer visionsystems is threatening their application in the real life and insafety-critical applications. Necessarily, Finding adversarial examples areimportant to detect susceptible models to attack and take safeguard measures toovercome the adversarial attacks. In this regard, MCS 2018 Adversarial Attackson Black Box Face Recognition challenge aims to facilitate the research offinding new adversarial attack techniques and their effectiveness in generatingadversarial examples. In this challenge, the attack"s nature is targeted-attackon the black-box neural network where we have no knowledge about black-block"sinner structure. The attacker must modify a set of five images of a singleperson so that the neural network miss-classify them as target image which is aset of five images of another person. In this competition, we applied MomentumDiverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) to make anadversarial attack on black-box face recognition system. We tested our methodon MCS 2018 Adversarial Attacks on Black Box Face Recognition challenge andfound competitive result. Our solution got validation score 1.404 which betterthan baseline score 1.407 and stood 14 place among 132 teams in theleader-board. Further improvement can be achieved by finding improved featureextraction from source image, carefully chosen hyper-parameters, findingimproved substitute model of the black-box and better optimization method.

Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method  (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box  Face Recognition System