Detecting Adversarial Inputs by Looking in the black box

  • Carrara, Fabio and Falchi, Fabrizio and Amato, Giuseppe, and Becarelli, Rudy and Caldelli R
N/ACitations
Citations of this article
2Readers
Mendeley users who have this article in their library.

Abstract

The astonishing and cryptic effectiveness of Deep Neural Networks comes with the critical vulnerability to adversarial inputs — samples maliciously crafted to confuse and hinder machine learning models. Insights into the internal representations learned by deep models can help to explain their decisions and estimate their confidence, which can enable us to trace, characterise, and filter out adversarial attacks.

Cite

CITATION STYLE

APA

Carrara, Fabio and Falchi, Fabrizio and Amato, Giuseppe, and Becarelli, Rudy and Caldelli, R. (2019). Detecting Adversarial Inputs by Looking in the black box. ERCIM News, (116). Retrieved from http://www.nmis.isti.cnr.it/falchi/Pub/2019-ERCIMNews116_Adv.pdf

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free