Understanding the risk factors of learning in adversarial environments

Authors:
Blaine Nelson;Battista Biggio;Pavel Laskov
Affiliations:
University of Tübingen, Tübingen, Germany;Department of Electrical and Electronic Engineering, University of Cagliari, Italy;University of Tübingen, Tübingen, Germany
Venue:
Proceedings of the 4th ACM workshop on Security and artificial intelligence
Year:
2011

Citing 10
Cited 0

Learning in the presence of malicious errors

SIAM Journal on Computing
The nature of statistical learning theory

The nature of statistical learning theory
Adversarial classification

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
Adversarial learning

Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
Prediction, Learning, and Games

Prediction, Learning, and Games
Nightmare at test time: robust learning by feature deletion

ICML '06 Proceedings of the 23rd international conference on Machine learning
Analysis of Perceptron-Based Active Learning

The Journal of Machine Learning Research
A framework for quantitative security analysis of machine learning

Proceedings of the 2nd ACM workshop on Security and artificial intelligence
Robustness and Regularization of Support Vector Machines

The Journal of Machine Learning Research
The security of machine learning

Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Learning for security applications is an emerging field where adaptive approaches are needed but are complicated by changing adversarial behavior. Traditional approaches to learning assume benign errors in data and thus may be vulnerable to adversarial errors. In this paper, we incorporate the notion of adversarial corruption directly into the learning framework and derive a new criteria for classifier robustness to adversarial contamination.