Automated Attacks on Compression-Based Classifiers
Methods of compression-based text classification have proven their usefulness for various applications. However, in some classification problems, such as spam filtering, a classifier confronts one or many adversaries willing to induce errors in the classifier's judgment on certain kinds of inpu...
| Main Author: | |
|---|---|
| Other Authors: | |
| Language: | en_US |
| Published: |
University of Oregon
2014
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1794/18439 |