Exploiting random perturbations to defend against adversarial attacks

Pawel Zawistowski; Bartlomiej Twardowski

doi:10.1117/12.2501606

1 October 2018 Exploiting random perturbations to defend against adversarial attacks

Pawel Zawistowski, Bartlomiej Twardowski

Proceedings Volume 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018; 108082N (2018) https://doi.org/10.1117/12.2501606
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 2018, Wilga, Poland

Abstract

Adversarial examples are deliberately crafted data points which aim to induce errors in machine learning models. This phenomenon has gained much attention recently, especially in the field of image classification, where many methods have been proposed to generate such malicious examples. In this paper we focus on defending a trained model against such attacks by introducing randomness to its inputs.

Citation Download Citation

Pawel Zawistowski and Bartlomiej Twardowski "Exploiting random perturbations to defend against adversarial attacks", Proc. SPIE 10808, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2018, 108082N (1 October 2018); https://doi.org/10.1117/12.2501606

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available