Evaluating data distribution and drift vulnerabilities of machine learning algorithms in secure and adversarial environments

Kevin Nelson; George Corbin; Misty Blowers

doi:10.1117/12.2053045

22 May 2014 Evaluating data distribution and drift vulnerabilities of machine learning algorithms in secure and adversarial environments

Kevin Nelson, George Corbin, Misty Blowers

Author Affiliations +

Proceedings Volume 9119, Machine Intelligence and Bio-inspired Computation: Theory and Applications VIII; 911904 (2014) https://doi.org/10.1117/12.2053045
Event: SPIE Sensing Technology + Applications, 2014, Baltimore, MD, United States

Abstract

Machine learning is continuing to gain popularity due to its ability to solve problems that are difficult to model using conventional computer programming logic. Much of the current and past work has focused on algorithm development, data processing, and optimization. Lately, a subset of research has emerged which explores issues related to security. This research is gaining traction as systems employing these methods are being applied to both secure and adversarial environments. One of machine learning’s biggest benefits, its data-driven versus logic-driven approach, is also a weakness if the data on which the models rely are corrupted. Adversaries could maliciously influence systems which address drift and data distribution changes using re-training and online learning. Our work is focused on exploring the resilience of various machine learning algorithms to these data-driven attacks. In this paper, we present our initial findings using Monte Carlo simulations, and statistical analysis, to explore the maximal achievable shift to a classification model, as well as the required amount of control over the data.

Citation Download Citation

Kevin Nelson, George Corbin, and Misty Blowers "Evaluating data distribution and drift vulnerabilities of machine learning algorithms in secure and adversarial environments", Proc. SPIE 9119, Machine Intelligence and Bio-inspired Computation: Theory and Applications VIII, 911904 (22 May 2014); https://doi.org/10.1117/12.2053045

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