Compression for anti-adversarial learning

Authors:
Yan Zhou;Meador Inge;Murat Kantarcioglu
Affiliations:
Erik Jonnson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX;Mentor Graphics Corporation, Mobile, AL;Erik Jonnson School of Engineering and Computer Science, University of Texas at Dallas, Richardson, TX
Venue:
PAKDD'11 Proceedings of the 15th Pacific-Asia conference on Advances in knowledge discovery and data mining - Volume Part II
Year:
2011

Citing 8
Cited 0

Data compression using dynamic Markov modelling

The Computer Journal
Arithmetic coding for data compression

Communications of the ACM
Compression and Coding Algorithms

Compression and Coding Algorithms
The Design and Analysis of Efficient Lossless Data Compression Systems

The Design and Analysis of Efficient Lossless Data Compression Systems
Compression and Machine Learning: A New Perspective on Feature Space Vectors

DCC '06 Proceedings of the Data Compression Conference
Spam Filtering Using Statistical Data Compression Models

The Journal of Machine Learning Research
A Multiple Instance Learning Strategy for Combating Good Word Attacks on Spam Filters

The Journal of Machine Learning Research
Malware detection using adaptive data compression

Proceedings of the 1st ACM workshop on Workshop on AISec

Quantified Score

Hi-index	0.00

Visualization

Abstract

We investigate the susceptibility of compression-based learning algorithms to adversarial attacks. We demonstrate that compression-based algorithms are surprisingly resilient to carefully plotted attacks that can easily devastate standard learning algorithms. In the worst case where we assume the adversary has a full knowledge of training data, compression-based algorithms failed as expected. We tackle the worst case with a proposal of a new technique that analyzes subsequences strategically extracted from given data. We achieved near-zero performance loss in the worst case in the domain of spam filtering.